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

    Neuronpedia

    INDEX
    Explanations

    probability

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.07
    יים
    -0.07
     mañana
    -0.06
     Arrays
    -0.06
     princess
    -0.06
     ل
    -0.06
    Je
    -0.06
     fica
    -0.06
    討
    -0.06
     tight
    -0.06
    POSITIVE LOGITS
    RequestBody
    0.07
    ongodb
    0.07
    _accessible
    0.07
    _IDLE
    0.07
     абсол
    0.07
    .DropTable
    0.07
     dön
    0.07
    transform
    0.07
    cerpt
    0.07
    apture
    0.07
    Act Density 0.044%

    No Known Activations