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

    Neuronpedia

    INDEX
    Explanations

    mathematical notation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ري
    -0.07
     redraw
    -0.07
     OID
    -0.07
    _rsa
    -0.07
     dirt
    -0.07
    	RTE
    -0.07
    _FALL
    -0.06
    �
    -0.06
     appName
    -0.06
    _features
    -0.06
    POSITIVE LOGITS
    STRU
    0.07
    斗
    0.06
     Bü
    0.06
    тора
    0.06
     professors
    0.06
    uong
    0.06
     Joseph
    0.06
     texas
    0.06
    aldi
    0.06
    ayi
    0.06
    Act Density 0.014%

    No Known Activations