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

    Neuronpedia

    INDEX
    Explanations

    wide

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    riwal
    -0.68
    uxxxx
    -0.56
    dafx
    -0.51
    aarrggbb
    -0.51
    GMENT
    -0.50
    gever
    -0.49
     réfé
    -0.49
    πον
    -0.49
     Riders
    -0.48
    __':
    -0.48
    POSITIVE LOGITS
     dynamic
    0.63
     nahilalakip
    0.62
    afficheront
    0.61
     Dynamic
    0.61
    الحياه
    0.60
    出版年
    0.59
    脚注の使い方
    0.59
    Jeografia
    0.59
     dinámico
    0.57
    bout
    0.56
    Act Density 0.001%

    No Known Activations