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

    Neuronpedia

    INDEX
    Explanations

    You

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     j
    -0.06
     OL
    -0.06
     Arabs
    -0.06
     přiroz
    -0.06
     servo
    -0.06
    -wh
    -0.06
     mat
    -0.06
    แ
    -0.06
    иля
    -0.06
    appro
    -0.06
    POSITIVE LOGITS
     определить
    0.07
    uong
    0.07
     Despite
    0.07
    ��
    0.06
    .getPage
    0.06
    scription
    0.06
    Kitchen
    0.06
     ид
    0.06
    ('_
    0.06
    _grp
    0.06
    Act Density 0.027%

    No Known Activations