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

    Neuronpedia

    INDEX
    Explanations

    standards

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	dist
    -0.07
    	client
    -0.07
     blok
    -0.07
     binary
    -0.07
     ask
    -0.07
     Gupta
    -0.07
    ToF
    -0.06
     intf
    -0.06
     skeptical
    -0.06
     pois
    -0.06
    POSITIVE LOGITS
    _charset
    0.08
    �
    0.07
    公告
    0.06
    ennon
    0.06
     réuss
    0.06
     Dipl
    0.06
    _EVENT
    0.06
     EMAIL
    0.06
     Hemp
    0.06
    ีน
    0.06
    Act Density 0.065%

    No Known Activations