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

    Neuronpedia

    INDEX
    Explanations

    const

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Increment
    -0.07
     vysok
    -0.07
    dados
    -0.07
    Movies
    -0.07
    邪
    -0.07
    	layer
    -0.07
    KY
    -0.07
     Meyer
    -0.07
    REDIT
    -0.06
     SIGNAL
    -0.06
    POSITIVE LOGITS
     const
    0.13
     Const
    0.13
    Const
    0.11
    const
    0.10
    	const
    0.10
    _const
    0.09
    (const
    0.09
     CONST
    0.08
    (Const
    0.08
    ,const
    0.07
    Act Density 0.003%

    No Known Activations