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

    Neuronpedia

    INDEX
    Explanations

    *

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     состоит
    -0.07
    رفت
    -0.07
    '],
↵
    -0.07
    卷
    -0.07
     Tên
    -0.07
     Cached
    -0.07
     đổi
    -0.07
    stackpath
    -0.07
    ('')↵
    -0.06
     Pee
    -0.06
    POSITIVE LOGITS
    LS
    0.07
    YN
    0.06
    yn
    0.06
    _TYP
    0.06
    FS
    0.06
     Canal
    0.06
     steep
    0.06
    ammo
    0.06
     millis
    0.06
     obtain
    0.06
    Act Density 0.000%

    No Known Activations