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

    Neuronpedia

    INDEX
    Explanations

    face

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     componentDid
    -0.07
    �
    -0.06
     Any
    -0.06
     Path
    -0.06
     Moto
    -0.06
     |
↵
    -0.06
    аст
    -0.06
    ύτε
    -0.06
     маг
    -0.06
    _OLD
    -0.06
    POSITIVE LOGITS
    Sac
    0.07
     Occupational
    0.06
    aspect
    0.06
    .De
    0.06
    मन
    0.06
    neighbors
    0.06
     refusal
    0.06
    ství
    0.06
    _preds
    0.06
    (ds
    0.06
    Act Density 0.003%

    No Known Activations