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

    Neuronpedia

    INDEX
    Explanations

    מה השעה?

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Aś
    1.01
     sofas
    1.00
     glLightfv
    0.98
     glTexCoord
    0.96
     custList
    0.96
     funciona
    0.96
     interstitiis
    0.96
     precludes
    0.96
     imassa
    0.95
     gahet
    0.95
    POSITIVE LOGITS
    א
    1.14
    כ
    1.12
     כ
    1.10
    מ
    1.09
     ע
    1.07
    ל
    1.05
    ב
    1.05
    ס
    1.05
    ה
    1.04
     א
    1.03
    Act Density 0.004%

    No Known Activations