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
    �
    -0.07
    	List
    -0.07
     -------------------------------------------------------------------------
    -0.07
    ntp
    -0.06
     университ
    -0.06
     Strap
    -0.06
    referrer
    -0.06
     всю
    -0.06
     násled
    -0.06
     अन
    -0.06
    POSITIVE LOGITS
    ーバ
    0.07
    Winter
    0.06
    itters
    0.06
    annt
    0.06
    Š
    0.06
    idges
    0.06
    ges
    0.06
    Assignable
    0.06
    olum
    0.06
    ідом
    0.06
    Act Density 0.014%

    No Known Activations