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

    Neuronpedia

    INDEX
    Explanations

    quantifying words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ')"
    0.60
     যেকোনো
    0.56
    洱
    0.56
     newfound
    0.56
     daisies
    0.56
     وجہ
    0.54
     pessimism
    0.54
    ၊
    0.54
     renewals
    0.54
     রোগ
    0.54
    POSITIVE LOGITS
    on
    1.21
    of
    1.04
    ي
    1.02
    am
    0.99
    r
    0.99
    ak
    0.97
    ر
    0.96
    er
    0.96
    p
    0.93
    T
    0.92
    Act Density 0.211%

    No Known Activations