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

    Neuronpedia

    INDEX
    Explanations

    list items and descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ্রের
    0.43
     wholes
    0.40
     Exact
    0.37
    输
    0.37
    fa
    0.37
     underlying
    0.37
     obliv
    0.37
    คโนโล
    0.36
    cens
    0.36
    ]{
    0.35
    POSITIVE LOGITS
    LOTRE
    0.51
     الشباب
    0.45
     गुरु
    0.45
    Glide
    0.44
     buena
    0.41
     সিভি
    0.41
    गुरु
    0.41
    Nancy
    0.41
     хорошее
    0.41
     jóvenes
    0.40
    Act Density 0.000%

    No Known Activations