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

    Neuronpedia

    INDEX
    Explanations

    first item of a numbered list

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ä
    0.76
    and
    0.70
     and
    0.65
    et
    0.60
    t
    0.60
    া
    0.57
    т
    0.57
    f
    0.52
    一
    0.52
    от
    0.51
    POSITIVE LOGITS
     פ
    0.51
     multitudes
    0.50
     將
    0.49
     Име
    0.49
     Фили
    0.48
     Saccharomyces
    0.47
     కొన్ని
    0.47
     ຂ
    0.47
     ك
    0.46
    ני
    0.46
    Act Density 0.093%

    No Known Activations