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

    Neuronpedia

    INDEX
    Explanations

    numbers and units

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    sided
    1.09
    তম
    1.03
    茦
    1.02
    sides
    1.02
    Му
    1.02
    WIDTH
    1.01
     около
    1.00
    Щ
    1.00
    textArea
    1.00
     আপনার
    0.99
    POSITIVE LOGITS
    urri
    0.95
    zelfde
    0.92
    onRequest
    0.92
     able
    0.91
    irne
    0.91
    りん
    0.90
    apore
    0.88
     definitively
    0.86
     esp
    0.86
    ραγ
    0.86
    Act Density 0.000%

    No Known Activations