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

    Neuronpedia

    INDEX
    Explanations

    fitness

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     CPA
    -0.08
     human
    -0.08
     accept
    -0.07
    ldr
    -0.07
     Romeo
    -0.07
     opět
    -0.07
     nhau
    -0.06
    ACCEPT
    -0.06
     아닌
    -0.06
     عزیز
    -0.06
    POSITIVE LOGITS
    eea
    0.06
    imony
    0.06
    lobals
    0.06
     yan
    0.06
     lleg
    0.06
    ponsors
    0.06
    /sources
    0.06
    /st
    0.06
    ór
    0.06
    альному
    0.05
    Act Density 0.026%

    No Known Activations