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
     επίσης
    -0.07
     hardness
    -0.06
    項
    -0.06
     Αρχ
    -0.06
     مقام
    -0.06
     трь
    -0.06
    Mag
    -0.06
     Bodies
    -0.06
     agr
    -0.06
     एक
    -0.06
    POSITIVE LOGITS
     const
    0.09
    const
    0.09
    (const
    0.09
    	const
    0.08
    `=
    0.07
    -community
    0.07
    dbo
    0.06
    ongan
    0.06
    _ci
    0.06
    <const
    0.06
    Act Density 0.006%

    No Known Activations