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

    Neuronpedia

    INDEX
    Explanations

    programming questions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	name
    -0.07
    stddef
    -0.07
     Crescent
    -0.07
     instinct
    -0.07
    DH
    -0.07
    handleRequest
    -0.06
    rep
    -0.06
    룰
    -0.06
    collect
    -0.06
    مين
    -0.06
    POSITIVE LOGITS
    🍇
    0.09
    .gradle
    0.07
    举起
    0.07
     wiel
    0.07
    ]+=
    0.07
    功用
    0.07
    浙江省
    0.07
     Orioles
    0.07
    拼音
    0.07
    =ax
    0.06
    Act Density 0.063%

    No Known Activations