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

    Neuronpedia

    INDEX
    Explanations

    blocking

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    STOP
    -0.07
    visited
    -0.07
     mimeType
    -0.07
    _EXEC
    -0.07
     toast
    -0.07
    River
    -0.07
    公园
    -0.07
    ardi
    -0.07
     ruler
    -0.07
     River
    -0.07
    POSITIVE LOGITS
     nuestros
    0.07
     appointments
    0.07
     обращ
    0.07
    뎃
    0.07
    гр
    0.07
     бл
    0.07
     prec
    0.07
    你是
    0.07
     één
    0.07
    降价
    0.07
    Act Density 0.001%

    No Known Activations