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

    Neuronpedia

    INDEX
    Explanations

    ales

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ASON
    -0.06
     Tür
    -0.06
     House
    -0.06
    _memory
    -0.06
     остан
    -0.06
    _median
    -0.06
     partes
    -0.06
    House
    -0.06
    (['/
    -0.06
     pixel
    -0.06
    POSITIVE LOGITS
     smirk
    0.07
     �
    0.07
     delightful
    0.06
     Incorrect
    0.06
    .TRA
    0.06
    /styles
    0.06
    ating
    0.06
     probabil
    0.06
    فاق
    0.06
    �
    0.06
    Act Density 0.003%

    No Known Activations