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

    Neuronpedia

    INDEX
    Explanations

    physical altercations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     fig
    -0.07
     Bug
    -0.07
    _usuario
    -0.06
     Schumer
    -0.06
     bug
    -0.06
    Lot
    -0.06
    há
    -0.06
    شار
    -0.06
     proofs
    -0.06
    TON
    -0.06
    POSITIVE LOGITS
    }"↵
    0.06
    .=
    0.06
    lias
    0.06
     amnesty
    0.06
     Köy
    0.06
     نقش
    0.06
     literal
    0.06
     knocking
    0.06
    othy
    0.06
    зації
    0.06
    Act Density 0.013%

    No Known Activations