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

    Neuronpedia

    INDEX
    Explanations

    x

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     верес
    -0.07
     кла
    -0.06
    िह
    -0.06
    ULE
    -0.06
    iless
    -0.06
    jq
    -0.06
     pile
    -0.06
     книж
    -0.06
     سن
    -0.06
     escalating
    -0.06
    POSITIVE LOGITS
     λειτουργ
    0.07
     genç
    0.06
    )V
    0.06
    [label
    0.06
    Chuck
    0.06
     Blanch
    0.06
    %\
    0.06
     equation
    0.06
     Supern
    0.06
     funkce
    0.06
    Act Density 0.000%

    No Known Activations