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

    Neuronpedia

    INDEX
    Explanations

    חיים

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     confiance
    0.74
    চিব
    0.72
     asimismo
    0.70
    unningham
    0.69
    leness
    0.69
     shorter
    0.68
    IDENCE
    0.68
    ത്മ
    0.68
    wick
    0.67
    arthy
    0.67
    POSITIVE LOGITS
    躲
    0.76
     Conclusions
    0.75
     വാർത്ത
    0.74
    罘
    0.74
    Enlaces
    0.74
    athe
    0.74
    diyl
    0.73
    菓子
    0.72
    Prog
    0.72
    になると
    0.72
    Act Density 0.032%

    No Known Activations