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

    Neuronpedia

    INDEX
    Explanations

    range

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -arm
    -0.07
     justo
    -0.07
    _detalle
    -0.07
    Performance
    -0.06
     enthusiasts
    -0.06
     最
    -0.06
    报告
    -0.06
     بار
    -0.06
     �
    -0.06
     рад
    -0.06
    POSITIVE LOGITS
     konuştu
    0.07
    -------------
    0.07
    _________________↵↵
    0.07
    �은
    0.07
    District
    0.06
    Proceed
    0.06
    ragen
    0.06
    _DRV
    0.06
    _MARKER
    0.06
    цький
    0.06
    Act Density 0.000%

    No Known Activations