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

    Neuronpedia

    INDEX
    Explanations

    Release dates/times

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Sleeping
    -0.07
     REF
    -0.07
    孩子
    -0.06
    }],
    -0.06
    _REGEX
    -0.06
    ρος
    -0.06
     workbook
    -0.06
    _string
    -0.06
    roups
    -0.06
     library
    -0.06
    POSITIVE LOGITS
    ■■
    0.07
    $count
    0.07
    _but
    0.06
    Mate
    0.06
    .fore
    0.06
    aturated
    0.06
    DebugEnabled
    0.06
    	item
    0.06
    HAVE
    0.06
    lararası
    0.06
    Act Density 0.072%

    No Known Activations