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

    Neuronpedia

    INDEX
    Explanations

    parenthesis

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Jordan
    -0.08
     Bain
    -0.07
    Alias
    -0.07
     Temple
    -0.07
    BN
    -0.07
    璱
    -0.07
     Antony
    -0.07
     densely
    -0.07
     Ragnar
    -0.07
     Binder
    -0.07
    POSITIVE LOGITS
     ViewGroup
    0.07
    .ready
    0.07
    冶
    0.07
    %\
    0.07
    🍢
    0.07
     обеспеч
    0.07
    っきり
    0.07
    ключа
    0.07
    PREC
    0.07
     prosecution
    0.07
    Act Density 0.013%

    No Known Activations