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

    Neuronpedia

    INDEX
    Explanations

    code configuration files

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    合作
    -0.07
    _q
    -0.07
     μία
    -0.06
    城市
    -0.06
     які
    -0.06
     CITY
    -0.06
     WARRANTY
    -0.06
     цель
    -0.06
     буду
    -0.06
     mother
    -0.06
    POSITIVE LOGITS
    .tpl
    0.07
     Лі
    0.06
    entially
    0.06
    �
    0.06
    asonic
    0.06
    ुद
    0.06
    .PageSize
    0.06
     outfile
    0.06
    ynec
    0.06
    щим
    0.06
    Act Density 0.018%

    No Known Activations