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

    Neuronpedia

    INDEX
    Explanations

    credit

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ublik
    -0.09
     demokr
    -0.08
    راهيم
    -0.07
    να
    -0.07
     Amerika
    -0.07
     Demokratie
    -0.07
     perfeita
    -0.07
     demon
    -0.07
     kommun
    -0.07
     america
    -0.07
    POSITIVE LOGITS
     arbre
    0.08
     végét
    0.08
    -Ar
    0.08
    Unnamed
    0.08
     mặt
    0.07
     funcionamento
    0.07
     fullness
    0.07
     imóvel
    0.07
     состояния
    0.07
     tuft
    0.07
    Act Density 0.000%

    No Known Activations