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

    Neuronpedia

    INDEX
    Explanations

    for

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    "%
    -0.07
    hc
    -0.07
    pieces
    -0.06
    byss
    -0.06
     бюдж
    -0.06
     Jesus
    -0.06
    ография
    -0.06
    )");↵
    -0.06
    lero
    -0.06
    ملكة
    -0.06
    POSITIVE LOGITS
    Retry
    0.07
     Skipping
    0.07
     supernatural
    0.06
    _removed
    0.06
     dataType
    0.06
     şeyler
    0.06
    /workspace
    0.06
    .We
    0.06
    /ss
    0.06
     cherished
    0.06
    Act Density 0.047%

    No Known Activations