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
     CONTR
    -0.07
    |--
    -0.06
     elektr
    -0.06
    FACT
    -0.06
    _id
    -0.06
    ldap
    -0.06
    qr
    -0.06
    cdr
    -0.06
     Pirate
    -0.06
    pix
    -0.06
    POSITIVE LOGITS
     Smarty
    0.07
    �
    0.07
    dığı
    0.07
     Within
    0.06
     "'",
    0.06
    んです
    0.06
    practice
    0.06
    Declare
    0.06
    SCRIBE
    0.06
    Than
    0.06
    Act Density 0.003%

    No Known Activations