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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     #__
    -0.29
    illac
    -0.26
    ungle
    -0.25
     stereotype
    -0.25
    ç²¾èĩ´
    -0.24
    accumulate
    -0.24
    ä¸ĢèĤ¡
    -0.24
    redient
    -0.24
    pit
    -0.23
     blanket
    -0.23
    POSITIVE LOGITS
    _calls
    0.30
    çµ®
    0.26
    went
    0.25
    caa
    0.25
    Markup
    0.25
    ä½Ļ家
    0.24
    èķ¨
    0.24
    )↵↵↵↵↵
    0.24
    æ¯ĶæĪij
    0.24
    æĬĬä»ĸ
    0.24
    Act Density 2.304%

    No Known Activations