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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     การแข
    -0.08
     (--
    -0.07
     nudity
    -0.07
    陣
    -0.06
     운영자
    -0.06
     straightforward
    -0.06
     Clear
    -0.06
    Cookies
    -0.06
    ici
    -0.06
     amps
    -0.06
    POSITIVE LOGITS
    νοντας
    0.06
    rastructure
    0.06
     использу
    0.06
    }/#{
    0.06
     CRT
    0.06
     premise
    0.06
    	not
    0.06
    ไม
    0.06
    remark
    0.06
    (namespace
    0.06
    Act Density 0.221%

    No Known Activations