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

    Neuronpedia

    INDEX
    Explanations

    adding fractions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    esthetic
    0.48
     ою
    0.46
    ologio
    0.46
     radiological
    0.46
    esthetics
    0.45
    zeitig
    0.44
     වෙ
    0.44
     unmistakable
    0.41
     phylogeny
    0.41
     confounding
    0.41
    POSITIVE LOGITS
    ទឹក
    0.56
    N
    0.56
        
    0.55
    Y
    0.53
    WATER
    0.52
     ഒരിക്ക
    0.52
    Portrait
    0.50
    APPLE
    0.50
    Never
    0.50
    MASTER
    0.50
    Act Density 0.000%

    No Known Activations