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

    Neuronpedia

    INDEX
    Explanations

    technical terms related to assembly visibility and attributes

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

    Code and technical language

    np_acts-logits-general · gemini-2.0-flash

    technical terms and code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    RTEX
    -0.50
    scriptcase
    -0.48
     Realtor
    -0.48
    ModelSerializer
    -0.47
     Vainqueur
    -0.47
     resourceCulture
    -0.47
    ConstraintMaker
    -0.46
    رشف
    -0.46
     kaya
    -0.46
     Velo
    -0.45
    POSITIVE LOGITS
     ComVisible
    1.60
     typelib
    0.81
    InSection
    0.66
     \]
    0.63
    engah
    0.63
     '\\;'
    0.59
     Faso
    0.58
    bleshooting
    0.58
    [:,:,
    0.58
    chism
    0.56
    Act Density 0.029%

    No Known Activations