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

    Neuronpedia

    INDEX
    Explanations

    September Hokkaido

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     déclaration
    0.40
     hate
    0.39
     Simplifying
    0.38
     घटना
    0.38
     আসনে
    0.38
     declared
    0.38
    declared
    0.37
     Declaration
    0.36
     تعمیر
    0.36
     طلعت
    0.36
    POSITIVE LOGITS
     Sak
    0.80
    Sak
    0.80
     sak
    0.75
    Sac
    0.70
     sac
    0.66
     Hokkaido
    0.66
    sak
    0.65
     Sac
    0.63
    SAC
    0.60
    sac
    0.59
    Act Density 0.005%

    No Known Activations