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

    Neuronpedia

    INDEX
    Explanations

    Damn it exclamations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ور
    2.02
     Allerdings
    1.94
    it
    1.90
     tribunals
    1.83
     wes
    1.80
    timestamps
    1.73
     allerdings
    1.71
    ه
    1.66
    ać
    1.63
    स
    1.63
    POSITIVE LOGITS
    О
    2.11
    Р
    1.81
    ly
    1.66
    ttet
    1.64
    К
    1.64
    其他
    1.62
    ter
    1.61
    І
    1.61
    Ր
    1.61
    ısı
    1.60
    Act Density 0.007%

    No Known Activations