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

    Neuronpedia

    INDEX
    Explanations

    code comments related to disabling linting rules

    oai_token-act-pair · gemini-2.0-flash

    disable

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    InputBorder
    -0.63
    mtrl
    -0.51
    AnimationFrame
    -0.50
    Gön
    -0.50
    NewRow
    -0.49
     typelib
    -0.48
    JsonKey
    -0.47
     actionBar
    -0.46
     ngân
    -0.45
    PositiveButton
    -0.45
    POSITIVE LOGITS
     transfieras
    0.79
    ptid
    0.58
    awtextra
    0.55
     nahilalakip
    0.54
     "",
    0.53
    ">//
    0.52
    phem
    0.51
    \\
    0.51
    zbęd
    0.51
    fjspx
    0.50
    Act Density 1.253%

    No Known Activations