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

    Neuronpedia

    INDEX
    Explanations

    -

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Show
    0.70
    ைக்கு
    0.70
    Research
    0.68
     მაშინ
    0.68
     desconocido
    0.68
    隧
    0.67
     Mentor
    0.66
    กระ
    0.64
     Porto
    0.63
    KURZ
    0.63
    POSITIVE LOGITS
     जीवित
    0.69
    ipated
    0.65
     Happy
    0.63
    ❼
    0.63
     FX
    0.63
     suffering
    0.61
    FX
    0.61
    快樂
    0.61
     happiest
    0.61
     merr
    0.60
    Act Density 0.003%

    No Known Activations