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

    Neuronpedia

    INDEX
    Explanations

    run-on sentences

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    isted
    -0.07
    107
    -0.07
     всю
    -0.07
    _offset
    -0.06
     optionally
    -0.06
     ř
    -0.06
     ranging
    -0.06
    .lp
    -0.06
    matching
    -0.06
     світ
    -0.06
    POSITIVE LOGITS
     मतलब
    0.07
    ุคคล
    0.06
    AppComponent
    0.06
    adalafil
    0.06
     ullam
    0.06
     IEEE
    0.06
     langue
    0.06
    .mul
    0.06
    :X
    0.06
    .newLine
    0.06
    Act Density 0.026%

    No Known Activations