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

    Neuronpedia

    INDEX
    Explanations

    Code/notation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    <C
    -0.06
    fab
    -0.06
     adept
    -0.06
    =P
    -0.06
     closets
    -0.05
     зал
    -0.05
    堂
    -0.05
    ,a
    -0.05
    .Broadcast
    -0.05
     fraternity
    -0.05
    POSITIVE LOGITS
    콜
    0.07
    Turkey
    0.07
     listeners
    0.07
    YYY
    0.06
     curved
    0.06
     إلي
    0.06
    cpy
    0.06
    Und
    0.06
    ights
    0.06
    _ld
    0.06
    Act Density 0.000%

    No Known Activations