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

    Neuronpedia

    INDEX
    Explanations

    codes, NAD, RAM, directly

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ther
    0.43
     fractionation
    0.42
     occurs
    0.40
     کئے
    0.38
     doğrud
    0.38
     COMMENTS
    0.38
     발생
    0.37
     berarti
    0.37
     Vich
    0.37
    Lag
    0.37
    POSITIVE LOGITS
     Ната
    0.42
    來到
    0.41
     Hooper
    0.40
    ्मी
    0.40
    ampilkan
    0.38
    លេ
    0.37
    ომ
    0.37
    騏
    0.37
    篩
    0.37
    oughton
    0.37
    Act Density 0.000%

    No Known Activations