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

    Neuronpedia

    INDEX
    Explanations

    ID

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     visc
    -0.08
     Graz
    -0.08
     الانت
    -0.07
    .sz
    -0.07
    líč
    -0.07
     Reason
    -0.07
    seau
    -0.06
     twist
    -0.06
    _named
    -0.06
    -orange
    -0.06
    POSITIVE LOGITS
    FUL
    0.07
     fond
    0.07
    _RESERVED
    0.07
    ưới
    0.06
    rites
    0.06
    重点
    0.06
    0.06
     Wiki
    0.06
    \Auth
    0.06
    iked
    0.06
    Act Density 0.001%

    No Known Activations