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

    Neuronpedia

    INDEX
    Explanations

    In

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     DAMAGE
    -0.07
     unit
    -0.07
     attaching
    -0.07
    _frequency
    -0.06
    	hs
    -0.06
     BB
    -0.06
    BALL
    -0.06
     axes
    -0.06
    sehen
    -0.06
     illustrated
    -0.06
    POSITIVE LOGITS
    .intValue
    0.07
    �
    0.07
     แหล
    0.07
     Arrow
    0.06
    _WIFI
    0.06
     داخل
    0.06
    WillDisappear
    0.06
     Spacer
    0.06
    >/<
    0.06
     пропози
    0.06
    Act Density 0.112%

    No Known Activations