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

    Neuronpedia

    INDEX
    Explanations

    Let's begin

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ра
    1.41
    ли
    1.36
    ना
    1.35
    ي
    1.32
    한
    1.27
    ни
    1.25
    é
    1.24
    THING
    1.22
    쪽
    1.17
    ি
    1.16
    POSITIVE LOGITS
    jenigen
    1.12
    ان
    1.09
    на
    1.07
    ts
    0.98
    ämän
    0.97
    iquetas
    0.95
    γωγ
    0.94
    വൃത്തി
    0.93
    ting
    0.92
    seekBar
    0.89
    Act Density 0.134%

    No Known Activations