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

    Neuronpedia

    INDEX
    Explanations

    -

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     grease
    -0.07
    ορ
    -0.07
    打开
    -0.07
    346
    -0.07
    UBLISH
    -0.07
     Guard
    -0.06
     landing
    -0.06
    perience
    -0.06
    培训
    -0.06
    _Final
    -0.06
    POSITIVE LOGITS
    ');?></
    0.06
    ologically
    0.06
     ±
    0.06
     Adri
    0.06
     Bolton
    0.06
    PX
    0.06
    result
    0.06
     JNI
    0.06
     asbestos
    0.06
    .fl
    0.06
    Act Density 0.006%

    No Known Activations