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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    <|eot_id|>
    -0.06
     Castillo
    -0.06
    /op
    -0.06
    India
    -0.06
     CHRIST
    -0.06
     cloudy
    -0.06
    	let
    -0.06
    秀
    -0.06
    ickers
    -0.06
    _similarity
    -0.06
    POSITIVE LOGITS
    >}
    0.07
    ]='\
    0.07
     τ
    0.07
     هیچ
    0.07
    ]";↵
    0.07
    (Database
    0.06
    *);↵
    0.06
    JKLMNOP
    0.06
    )});↵
    0.06
     Εκ
    0.06
    Act Density 0.175%

    No Known Activations