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

    Neuronpedia

    INDEX
    Explanations

    face as form

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Obtain
    1.12
     FURTHER
    1.12
     준비
    1.12
     место
    1.11
    PLICATIONS
    1.10
     Frankel
    1.09
     reiterate
    1.09
    /∂
    1.08
     궁
    1.07
     р
    1.07
    POSITIVE LOGITS
    事故
    0.97
     latar
    0.97
    sina
    0.96
    トリ
    0.95
    shim
    0.95
    imble
    0.94
    implicit
    0.93
    istor
    0.93
    such
    0.93
    ബു
    0.90
    Act Density 0.061%

    No Known Activations