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

    Neuronpedia

    INDEX
    Explanations

    programming and technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     palk
    0.71
    艶
    0.71
    ambio
    0.69
     prens
    0.64
    ល
    0.63
    തില്‍
    0.63
     пі
    0.62
    езде
    0.62
    ந்தில்
    0.61
     جوا
    0.61
    POSITIVE LOGITS
    STRACT
    0.73
     још
    0.73
    喍
    0.72
    Solver
    0.71
    abilă
    0.71
    igram
    0.71
     kali
    0.71
     eliminates
    0.71
     еще
    0.69
     bayi
    0.69
    Act Density 0.000%

    No Known Activations