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

    Neuronpedia

    INDEX
    Explanations

    code snippets and programming-related terminology

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

    File paths and directory names

    np_acts-logits-general · gemini-2.0-flash

    file paths and code delimiters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     “
    -0.25
     the
    -0.23
     in
    -0.21
     ‘
    -0.21
     a
    -0.21
     van
    -0.21
     an
    -0.20
     K
    -0.20
     B
    -0.20
     of
    -0.20
    POSITIVE LOGITS
     avoient
    0.84
     feroit
    0.83
     auroit
    0.82
     varandra
    0.82
     étoient
    0.81
     enfans
    0.79
     pouvoit
    0.76
     étoit
    0.76
     stället
    0.75
     chrétiens
    0.74
    Act Density 64.637%

    No Known Activations