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

    Neuronpedia

    INDEX
    Explanations

    CSS

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Hentet
    -0.84
     ruling
    -0.71
    taken
    -0.69
    出版年
    -0.68
    Referanser
    -0.63
     taken
    -0.63
     Ruling
    -0.61
    Datuak
    -0.60
    enumi
    -0.58
    ruling
    -0.56
    POSITIVE LOGITS
     Phry
    0.63
     Cæsar
    0.60
     out
    0.56
     Out
    0.55
    Out
    0.54
     Swain
    0.54
     Brutus
    0.54
    orteur
    0.54
    jspx
    0.53
     outta
    0.52
    Act Density 0.155%

    No Known Activations