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

    Neuronpedia

    INDEX
    Explanations

    model numbers and tech specs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    のも
    -0.07
    Tcp
    -0.07
    	wg
    -0.07
     conced
    -0.07
    pictured
    -0.06
    ItemCount
    -0.06
    Parms
    -0.06
     comer
    -0.06
     бед
    -0.06
     Чем
    -0.06
    POSITIVE LOGITS
     richness
    0.08
    ерим
    0.07
    _sex
    0.07
    json
    0.06
     parameter
    0.06
    TB
    0.06
     Fant
    0.06
     thông
    0.06
     TU
    0.06
    ÜR
    0.06
    Act Density 0.023%

    No Known Activations