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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    bdb
    -0.07
     Legion
    -0.06
     Nath
    -0.06
     نماید
    -0.06
     π
    -0.06
    	cache
    -0.06
    ecn
    -0.06
    Beat
    -0.06
     Blvd
    -0.06
    classnames
    -0.06
    POSITIVE LOGITS
     pretty
    0.07
    _json
    0.07
    ούς
    0.07
     proposing
    0.06
     premise
    0.06
    ูปแบบ
    0.06
     파일
    0.06
    pais
    0.06
    	while
    0.06
    ใส
    0.06
    Act Density 0.001%

    No Known Activations