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
    Bay
    -0.07
     Serena
    -0.07
    cache
    -0.06
    plotlib
    -0.06
     viability
    -0.06
    ACITY
    -0.06
    :{}
    -0.06
    -default
    -0.06
     Bosch
    -0.06
     puss
    -0.06
    POSITIVE LOGITS
     indicative
    0.07
     Ek
    0.06
     figur
    0.06
    用于
    0.06
     administer
    0.06
    ична
    0.06
     Interestingly
    0.06
    っき
    0.06
     emphasized
    0.06
     V
    0.06
    Act Density 0.062%

    No Known Activations