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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Research
    -0.08
    _VAL
    -0.07
    کش
    -0.06
    .baseUrl
    -0.06
    domain
    -0.06
     incest
    -0.06
    -case
    -0.06
    udd
    -0.06
    _adj
    -0.06
    PD
    -0.06
    POSITIVE LOGITS
    _mi
    0.06
    +:
    0.06
     یافت
    0.06
     кар
    0.06
    wcsstore
    0.06
    _OLD
    0.05
     sore
    0.05
     road
    0.05
    (Y
    0.05
     elles
    0.05
    Act Density 0.163%

    No Known Activations