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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Федераль
    -0.06
    lendir
    -0.06
     commuting
    -0.06
     siendo
    -0.06
     sensual
    -0.06
    bsites
    -0.06
    obierno
    -0.06
     příslu
    -0.06
     boycott
    -0.06
     ber
    -0.06
    POSITIVE LOGITS
     hedef
    0.07
     ROLE
    0.06
     confidently
    0.06
     whole
    0.06
     TELE
    0.06
    A
    0.06
    registry
    0.06
     KK
    0.06
    terra
    0.06
    isha
    0.06
    Act Density 0.047%

    No Known Activations