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

    Neuronpedia

    INDEX
    Explanations

    language and translation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    rade
    0.49
    enth
    0.48
    eks
    0.46
    rad
    0.46
    izations
    0.46
    டக்கலை
    0.46
    കസ
    0.46
    apadani
    0.45
    8
    0.45
     கொடுத்து
    0.45
    POSITIVE LOGITS
    벌
    0.46
    맥
    0.44
    پل
    0.41
     Servicio
    0.41
    werk
    0.41
     यात्रा
    0.40
    영화
    0.40
    0.40
     resemble
    0.40
     డా
    0.40
    Act Density 0.006%

    No Known Activations