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

    Neuronpedia

    INDEX
    Explanations

    dates

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    262
    -0.07
     Marian
    -0.07
    .TextInput
    -0.06
     нав
    -0.06
     المص
    -0.06
     WHICH
    -0.06
    ього
    -0.06
     which
    -0.06
     난
    -0.06
    ổ
    -0.06
    POSITIVE LOGITS
     skup
    0.07
    Cancelled
    0.06
    otten
    0.06
    основ
    0.06
     remnants
    0.06
     $$$
    0.06
    ères
    0.06
    =require
    0.06
    .pending
    0.06
     desperately
    0.06
    Act Density 0.023%

    No Known Activations