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

    Neuronpedia

    INDEX
    Explanations

    application

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    莘
    -0.07
     ksz
    -0.07
    我省
    -0.07
    ຊ
    -0.07
    ಛ
    -0.07
     kidneys
    -0.07
    _editor
    -0.07
    _require
    -0.07
     reveal
    -0.06
     element
    -0.06
    POSITIVE LOGITS
     зав
    0.08
    ^-
    0.07
    ﯘ
    0.07
    ✨
    0.07
     APPRO
    0.07
    涡
    0.07
     Metropolitan
    0.07
     dragons
    0.07
     Extremely
    0.07
    附近的
    0.07
    Act Density 0.003%

    No Known Activations