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

    Neuronpedia

    INDEX
    Explanations

    code functions with types

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Б
    0.57
    И
    0.55
    р
    0.53
    ਾ
    0.52
    ോട്ട്
    0.51
    آ
    0.49
    Авто
    0.49
    А
    0.48
     Brexit
    0.48
    Ро
    0.47
    POSITIVE LOGITS
     haven
    0.49
    heba
    0.46
     mottled
    0.44
    ravy
    0.44
     balcon
    0.44
    CPC
    0.41
     depleted
    0.41
    haven
    0.41
     शुक्ल
    0.41
     buddhav
    0.40
    Act Density 0.001%

    No Known Activations