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

    Neuronpedia

    INDEX
    Explanations

    track things

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    艿
    0.41
     Paglinawan
    0.40
    蒇
    0.38
    抢
    0.38
    Ⲁ
    0.38
    成分
    0.37
    利用者
    0.37
    नक
    0.37
    ومو
    0.36
    修为
    0.36
    POSITIVE LOGITS
    klich
    0.42
    dre
    0.39
     దక్షిణ
    0.39
    ibr
    0.37
    aine
    0.37
    smoke
    0.37
    rod
    0.36
    glEnd
    0.36
    denes
    0.36
    mary
    0.36
    Act Density 0.000%

    No Known Activations