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
     crochet
    -0.07
    -opening
    -0.06
     "\(
    -0.06
    ประว
    -0.06
     สาข
    -0.06
     *_
    -0.06
     muscle
    -0.06
    нулся
    -0.06
    pod
    -0.06
     ')';↵
    -0.06
    POSITIVE LOGITS
     register
    0.08
     progressively
    0.06
    ALIGN
    0.06
     athleticism
    0.06
    chair
    0.06
    SUPER
    0.06
     smirk
    0.06
    (short
    0.06
     IDEA
    0.06
    GENER
    0.06
    Act Density 0.015%

    No Known Activations