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

    Neuronpedia

    INDEX
    Explanations

    mathematics

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    énement
    -0.10
    ènement
    -0.09
    enoside
    -0.09
    ованный
    -0.09
     etmək
    -0.08
     केला
    -0.08
     какой
    -0.08
     그
    -0.08
     должен
    -0.08
     ಒಂದು
    -0.08
    POSITIVE LOGITS
    -values
    0.34
     values
    0.33
    's
    0.30
    values
    0.30
    	values
    0.28
    들의
    0.26
    _values
    0.25
    ’s
    0.25
    Values
    0.25
     waarden
    0.24
    Act Density 0.306%

    No Known Activations