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

    Neuronpedia

    INDEX
    Explanations

    numerical operations and comparisons in code

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

    javascript code fragments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    tvguidetime
    -0.78
    enderror
    -0.74
    ValueStyle
    -0.71
    argout
    -0.71
     CanadaChoose
    -0.70
    interopRequire
    -0.69
     Савезне
    -0.66
    ੝
    -0.66
    CppMethod
    -0.65
    elemField
    -0.65
    POSITIVE LOGITS
     tratto
    0.30
     sidan
    0.28
     thereby
    0.28
    こともあります
    0.28
     poffible
    0.27
     endnu
    0.27
     bébés
    0.27
     retten
    0.27
     preuves
    0.26
     őket
    0.26
    Act Density 0.094%

    No Known Activations