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

    Neuronpedia

    INDEX
    Explanations

    Publication information

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Cards
    -0.07
     democrat
    -0.07
     Seite
    -0.06
    ascending
    -0.06
     Marian
    -0.06
     Cant
    -0.06
    .Model
    -0.06
    cobra
    -0.06
     Bs
    -0.06
    Forever
    -0.06
    POSITIVE LOGITS
    Sept
    0.06
     уси
    0.06
    _assignment
    0.06
     Higher
    0.06
     unnoticed
    0.06
     lineWidth
    0.06
    ;-
    0.06
    _HELP
    0.06
    ;n
    0.06
    .dk
    0.06
    Act Density 0.021%

    No Known Activations