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

    Neuronpedia

    INDEX
    Explanations

    warnings

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ColumnType
    -0.07
    ену
    -0.07
    252
    -0.06
    ени
    -0.06
    ову
    -0.06
    ของผ
    -0.06
     prze
    -0.06
    WebService
    -0.06
    _STAT
    -0.06
     zast
    -0.06
    POSITIVE LOGITS
     hypotheses
    0.07
     palm
    0.06
    	display
    0.06
    .effects
    0.06
    	config
    0.06
    検
    0.06
     langue
    0.06
    two
    0.06
     mistake
    0.06
     �
    0.06
    Act Density 0.080%

    No Known Activations