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

    Neuronpedia

    INDEX
    Explanations

    proportions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Nothing
    -0.07
    .None
    -0.07
    кры
    -0.07
    	date
    -0.06
     ку
    -0.06
    CONST
    -0.06
     Features
    -0.06
     null
    -0.06
    Height
    -0.06
    /var
    -0.06
    POSITIVE LOGITS
     Achilles
    0.07
    ποι
    0.06
     Ravens
    0.06
    ROLL
    0.06
    iswa
    0.06
    émon
    0.06
    (KEY
    0.06
     Jays
    0.06
     Texans
    0.06
    اپیم
    0.06
    Act Density 0.071%

    No Known Activations