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

    Neuronpedia

    INDEX
    Explanations

    normal or correct operation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    igious
    0.71
    anthrop
    0.71
     empirically
    0.69
    ệm
    0.68
    ແບບ
    0.67
    实
    0.66
     الفق
    0.66
     దీ
    0.66
     CALLBACK
    0.66
    新手
    0.65
    POSITIVE LOGITS
     normally
    2.60
    normally
    2.38
     Normally
    2.28
     normalmente
    2.14
    Normally
    2.08
     normalement
    2.06
     ordinarily
    1.80
     normal
    1.78
     normaal
    1.67
    Normal
    1.67
    Act Density 0.047%

    No Known Activations