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

    Neuronpedia

    INDEX
    Explanations

    terms related to naming and designating concepts

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

    naming or designation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    dafx
    -0.46
    EndContext
    -0.45
    currentColor
    -0.39
    blut
    -0.39
     &___
    -0.37
     pinulongan
    -0.36
    Zdrav
    -0.36
     الا
    -0.36
     SPC
    -0.36
     Shear
    -0.35
    POSITIVE LOGITS
     henceforth
    0.51
     dubbed
    0.48
     surla
    0.47
    gonic
    0.46
    umumkan
    0.46
     kiệm
    0.46
     nazy
    0.45
    called
    0.45
     called
    0.44
    rungsseite
    0.43
    Act Density 0.091%

    No Known Activations