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
    _Reference
    -0.07
     sammen
    -0.07
    (column
    -0.07
     Question
    -0.07
     <$
    -0.07
     vmax
    -0.06
     يو
    -0.06
     peak
    -0.06
     offseason
    -0.06
    _department
    -0.06
    POSITIVE LOGITS
    ільки
    0.07
     Mango
    0.07
     Evening
    0.06
    IMENT
    0.06
    yect
    0.06
    ANDLE
    0.06
    etc
    0.06
     kims
    0.06
    职业
    0.06
    -res
    0.06
    Act Density 0.012%

    No Known Activations