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
    ”
    -0.08
    ,”
    -0.07
     bere
    -0.07
    antic
    -0.07
     سنت
    -0.07
    ’s
    -0.07
    _br
    -0.07
     trận
    -0.07
    町
    -0.06
    inst
    -0.06
    POSITIVE LOGITS
    >");
↵
    0.06
    IDES
    0.06
    ";}↵
    0.06
    }';↵
    0.06
     Erotic
    0.06
     respondent
    0.06
    secret
    0.06
    mouseenter
    0.06
     UserID
    0.06
    >);↵
    0.06
    Act Density 0.196%

    No Known Activations