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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     treasure
    -0.07
     определ
    -0.06
    UND
    -0.06
    rze
    -0.06
    BOOLEAN
    -0.06
     озна
    -0.06
    utschen
    -0.05
    Creative
    -0.05
    .getDay
    -0.05
    jah
    -0.05
    POSITIVE LOGITS
     foi
    0.07
     Picks
    0.07
    那么
    0.07
    =z
    0.07
    олю
    0.06
    .AddInParameter
    0.06
    看着
    0.06
     नय
    0.06
    ้ย
    0.06
     проблема
    0.06
    Act Density 0.026%

    No Known Activations