Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    technical terminology and specific procedures related to methods and algorithms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Methods or procedures, often described or outlined

    np_acts-logits-general · gemini-2.0-flash

    described methods and procedures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ⓧ
    -0.45
    GenerationType
    -0.38
     <<<<<<<<<<<<<<
    -0.36
     Roskov
    -0.33
    ctically
    -0.33
    RenderAtEndOf
    -0.33
     yanı
    -0.32
     بيها
    -0.32
     آس
    -0.32
    Demografie
    -0.31
    POSITIVE LOGITS
     described
    1.48
     outlined
    1.43
     mentioned
    1.38
     listed
    1.37
     discussed
    1.23
     depicted
    1.20
    described
    1.19
     stated
    1.15
     specified
    1.13
     shown
    1.09
    Act Density 1.413%

    No Known Activations