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

    Neuronpedia

    INDEX
    Explanations

    multiple languages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ==>
    -0.08
     liever
    -0.08
     normalement
    -0.08
     관리자
    -0.08
     bets
    -0.07
    sun
    -0.07
     tetr
    -0.07
     ----------↵
    -0.07
     ------
    -0.07
    line
    -0.07
    POSITIVE LOGITS
     poised
    0.08
     чест
    0.08
    Pois
    0.07
     multiplex
    0.07
     VN
    0.07
     innocence
    0.07
     scrum
    0.07
     insiders
    0.07
    意
    0.07
     таким
    0.07
    Act Density 0.000%

    No Known Activations