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

    Neuronpedia

    INDEX
    Explanations

    Math symbols

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     х
    -0.06
    <Component
    -0.06
     volont
    -0.06
     Specs
    -0.06
     Infer
    -0.06
    _le
    -0.06
     intervene
    -0.06
     Вели
    -0.06
     veloc
    -0.06
     �
    -0.06
    POSITIVE LOGITS
    	Game
    0.06
    -the
    0.06
    昇
    0.06
     SSL
    0.06
    .ref
    0.06
    Abs
    0.06
    	F
    0.06
    符
    0.06
    Australian
    0.06
     productService
    0.06
    Act Density 0.007%

    No Known Activations