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

    Neuronpedia

    INDEX
    Explanations

    future certainty

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ly
    1.41
    ून
    1.06
    नी
    1.03
    ی
    1.03
    -\
    1.01
    রে
    0.98
    $)$.
    0.96
    ression
    0.93
    mAh
    0.92
    вать
    0.92
    POSITIVE LOGITS
    amette
    1.52
    oughby
    1.44
     inevitably
    1.36
     sicuramente
    1.34
     surely
    1.30
     tetapi
    1.29
     μπορού
    1.25
     undoubtedly
    1.25
    ows
    1.24
     πρέπει
    1.21
    Act Density 0.378%

    No Known Activations