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

    Neuronpedia

    INDEX
    Explanations

    prepared

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     nog
    -0.07
    Classes
    -0.07
     madd
    -0.06
     Hexatrigesimal
    -0.06
     представляет
    -0.06
    ья
    -0.06
    束
    -0.06
    assador
    -0.06
    _Var
    -0.06
     overlaps
    -0.06
    POSITIVE LOGITS
    .delivery
    0.06
     potential
    0.06
    ,options
    0.06
    Ready
    0.06
     Indian
    0.06
    (port
    0.06
     idea
    0.05
    _Dis
    0.05
     Sect
    0.05
     Thai
    0.05
    Act Density 0.016%

    No Known Activations