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

    Neuronpedia

    INDEX
    Explanations

    Some

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ICommand
    -0.06
     वजह
    -0.06
     بول
    -0.06
    اا
    -0.06
    forget
    -0.06
     leve
    -0.06
     Niger
    -0.06
    вей
    -0.06
     spree
    -0.06
     jihadists
    -0.06
    POSITIVE LOGITS
    /single
    0.07
     Helena
    0.06
    inant
    0.06
    /pass
    0.06
    イン
    0.06
    /red
    0.06
     џ
    0.06
    ,J
    0.06
    alon
    0.06
     تومان
    0.06
    Act Density 0.032%

    No Known Activations