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

    Neuronpedia

    INDEX
    Explanations

    words starting with an

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    聑
    0.41
    LPTMR
    0.37
     Derm
    0.37
    ปรา
    0.37
     داله
    0.37
    Hare
    0.36
    澗
    0.35
    AA
    0.35
     مذہب
    0.35
    雩
    0.35
    POSITIVE LOGITS
    jan
    0.56
    chal
    0.55
    swering
    0.55
    mol
    0.54
    ji
    0.52
    ubhav
    0.52
    isola
    0.51
    anda
    0.50
    antha
    0.49
    jali
    0.48
    Act Density 0.005%

    No Known Activations