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

    Neuronpedia

    INDEX
    Explanations

    or

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Watkins
    -0.07
     narcotics
    -0.07
    _CALC
    -0.07
     declines
    -0.07
    COD
    -0.07
    📹
    -0.06
     unsuccessfully
    -0.06
     traditions
    -0.06
     Brittany
    -0.06
     Conflict
    -0.06
    POSITIVE LOGITS
    /dc
    0.07
     Prä
    0.07
    .onStart
    0.07
    subscriber
    0.07
     membr
    0.07
    文献
    0.07
    	dfs
    0.07
    .JFrame
    0.07
    🏋
    0.07
    确切
    0.06
    Act Density 0.001%

    No Known Activations