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

    Neuronpedia

    INDEX
    Explanations

    Pul followed by umi, lover, py

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     concession
    0.81
    encephal
    0.78
    ীয়
    0.75
     കണ്ണ
    0.74
    ंधरा
    0.72
     frío
    0.71
     चिन्ह
    0.70
     anaerobic
    0.69
     teken
    0.69
    solete
    0.69
    POSITIVE LOGITS
    ገኙ
    0.73
    英国
    0.68
    aski
    0.67
    lished
    0.67
    ைப்
    0.65
     Pull
    0.65
    सौ
    0.64
    โปร
    0.64
    πος
    0.63
    国の
    0.63
    Act Density 0.002%

    No Known Activations