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

    Neuronpedia

    INDEX
    Explanations

    kind

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ربع
    -0.07
     budd
    -0.07
     않았다
    -0.06
    _typ
    -0.06
    زيد
    -0.06
    _prom
    -0.06
    είου
    -0.06
     Gujar
    -0.06
     سرد
    -0.06
    opped
    -0.06
    POSITIVE LOGITS
    ()]);↵
    0.06
    ");↵
    0.06
    WEBPACK
    0.06
     Sergeant
    0.06
    ]'
    0.06
    ỏ
    0.06
     Hai
    0.06
    icken
    0.06
     nghi
    0.06
    Non
    0.06
    Act Density 0.309%

    No Known Activations