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

    Neuronpedia

    INDEX
    Explanations

    programming, code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    wap
    -0.07
    /Data
    -0.06
     stagger
    -0.06
    green
    -0.06
     administer
    -0.06
    リング
    -0.06
    lore
    -0.06
     움
    -0.06
     pled
    -0.06
    -white
    -0.06
    POSITIVE LOGITS
     средств
    0.07
     adulte
    0.06
    яс
    0.06
    часно
    0.06
    _reporting
    0.06
     составе
    0.06
    :?
    0.06
    _CTRL
    0.06
    	endif
    0.06
    ？”↵↵
    0.06
    Act Density 0.000%

    No Known Activations