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

    Neuronpedia

    INDEX
    Explanations

    formulating hypotheses or questions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     içerisinde
    0.57
    瘓
    0.55
    貸款
    0.54
    اکي
    0.53
    懺
    0.51
     पूर्ण
    0.50
    完整
    0.50
     Salaries
    0.49
     Amongst
    0.49
    فهام
    0.49
    POSITIVE LOGITS
    (=
    0.76
    ・
    0.73
    ※
    0.72
    ≒
    0.67
     (=
    0.65
     indispensable
    0.63
    geqq
    0.62
     hoge
    0.60
    <0xE3>
    0.59
    leqq
    0.59
    Act Density 0.007%

    No Known Activations