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

    Neuronpedia

    INDEX
    Explanations

    ordinals and cardinals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    PWM
    0.70
     PWM
    0.65
     IgG
    0.65
    Bob
    0.61
    yog
    0.60
     iod
    0.58
     Yann
    0.57
     collim
    0.57
    ضان
    0.57
     astron
    0.56
    POSITIVE LOGITS
     seventh
    0.70
    nd
    0.66
     सात
    0.61
     sixth
    0.60
     felony
    0.60
    喬
    0.59
    sixth
    0.59
    位的
    0.59
     six
    0.59
     السادس
    0.58
    Act Density 0.003%

    No Known Activations