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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     appraisal
    -0.06
     Irish
    -0.06
    備
    -0.06
     Україн
    -0.06
    stoup
    -0.06
    development
    -0.06
    tron
    -0.06
    \Service
    -0.06
    )":
    -0.06
    stoupil
    -0.06
    POSITIVE LOGITS
    (LP
    0.07
     чуть
    0.07
     ".$_
    0.07
    ",__
    0.06
    izador
    0.06
     visita
    0.06
    gua
    0.06
    oppins
    0.06
    (constants
    0.06
     Пок
    0.06
    Act Density 0.095%

    No Known Activations