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

    Neuronpedia

    INDEX
    Explanations

    json

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -head
    -0.07
     places
    -0.07
    vetica
    -0.06
     '
    -0.06
    subject
    -0.06
     Observ
    -0.06
    174
    -0.06
     Compet
    -0.06
    licated
    -0.06
     #"
    -0.06
    POSITIVE LOGITS
     migrationBuilder
    0.07
     Honestly
    0.07
    .Clamp
    0.06
    .cat
    0.06
     حساب
    0.06
     эк
    0.06
     doğal
    0.06
     홈페이지
    0.06
     ör
    0.06
     společně
    0.06
    Act Density 0.023%

    No Known Activations