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

    Neuronpedia

    INDEX
    Explanations

    s

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Ut
    -0.07
    .IsMatch
    -0.07
     flee
    -0.07
    .CONFIG
    -0.07
    _TRAIN
    -0.06
     PRIVATE
    -0.06
    .isLoggedIn
    -0.06
     currentPosition
    -0.06
     SERVER
    -0.06
    ,col
    -0.06
    POSITIVE LOGITS
     squeezed
    0.07
    semi
    0.06
     bounced
    0.06
    47
    0.06
     виготов
    0.06
     Mev
    0.06
     Thickness
    0.06
    skin
    0.06
    408
    0.06
     disag
    0.06
    Act Density 0.000%

    No Known Activations