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

    Neuronpedia

    INDEX
    Explanations

    Technical/Academic texts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ostensibly
    -0.79
     ultimately
    -0.69
     inherently
    -0.66
     necessarily
    -0.66
     nécessairement
    -0.66
    SharedDtor
    -0.64
     aparentemente
    -0.63
    发表于
    -0.61
     necesariamente
    -0.60
    ThroughAttribute
    -0.60
    POSITIVE LOGITS
     myſelf
    0.72
     Monfieur
    0.64
     ſeveral
    0.61
     leaſt
    0.60
     ſame
    0.59
     purpoſe
    0.58
     poffible
    0.58
     pleaſure
    0.57
     faro
    0.57
     reaſon
    0.56
    Act Density 0.071%

    No Known Activations