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

    Neuronpedia

    INDEX
    Explanations

    des

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    River
    -0.08
     River
    -0.07
     AREA
    -0.07
     shining
    -0.07
     Scouts
    -0.07
    ADIO
    -0.07
    ucha
    -0.06
     Serve
    -0.06
    ackbar
    -0.06
    いる
    -0.06
    POSITIVE LOGITS
    ichick
    0.08
    @g
    0.07
    _VAR
    0.07
     臺
    0.07
    642
    0.06
    36
    0.06
     hdf
    0.06
     domic
    0.06
     �
    0.06
     distrib
    0.06
    Act Density 0.001%

    No Known Activations