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

    Neuronpedia

    INDEX
    Explanations

    aclass

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     energ
    -0.07
     trio
    -0.07
     ked
    -0.07
     또한
    -0.07
    ScrollIndicator
    -0.07
    Serialize
    -0.07
    虽说
    -0.07
     Sleeve
    -0.07
     또는
    -0.07
    _SECRET
    -0.07
    POSITIVE LOGITS
    万个
    0.07
    VERAGE
    0.07
    草案
    0.07
     Watching
    0.07
    ナル
    0.07
    مص
    0.06
    Ꮆ
    0.06
     crops
    0.06
    识
    0.06
     EXCEPTION
    0.06
    Act Density 0.000%

    No Known Activations