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

    Neuronpedia

    INDEX
    Explanations

    hebrew and english requests

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     tiga
    0.68
     traged
    0.67
     perde
    0.67
     incluindo
    0.64
     progreso
    0.64
     încep
    0.64
     programa
    0.64
     fotograf
    0.64
     investigador
    0.64
     álgebra
    0.64
    POSITIVE LOGITS
     מ
    1.16
    מ
    1.07
     ע
    1.06
     ה
    1.05
     מש
    1.05
     כ
    1.04
     א
    1.02
     המ
    1.01
     ב
    1.00
     לא
    0.98
    Act Density 0.013%

    No Known Activations