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

    Neuronpedia

    INDEX
    Explanations

    long or longer text

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ین
    1.14
    ב
    1.11
    ために
    1.03
    አ
    0.93
    }{
    0.92
    Officers
    0.91
    ک
    0.90
    ש
    0.90
    August
    0.89
    )}
    0.88
    POSITIVE LOGITS
    ור
    1.38
    ิ
    1.04
     divulg
    1.03
     configur
    0.97
     vend
    0.96
     cré
    0.96
     trifling
    0.95
     protracted
    0.93
     financi
    0.93
    ()=>{
    0.92
    Act Density 0.144%

    No Known Activations