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

    Neuronpedia

    INDEX
    Explanations

    formal structured text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    への
    -0.07
     آز
    -0.07
    .Temp
    -0.07
    _FAMILY
    -0.06
    	AM
    -0.06
     брон
    -0.06
     ör
    -0.06
    لف
    -0.06
    ращи
    -0.06
    的心
    -0.06
    POSITIVE LOGITS
     European
    0.07
    065
    0.07
    European
    0.07
     TODO
    0.06
     lamp
    0.06
     Dogs
    0.06
     Kenya
    0.06
    %p
    0.06
    ↵
↵
↵
↵
    0.06
    It
    0.06
    Act Density 0.000%

    No Known Activations