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

    Neuronpedia

    INDEX
    Explanations

    Varied news and scientific topics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Efq
    -1.22
     doubtnut
    -1.19
     pleaſure
    -1.19
     myſelf
    -1.16
     Monfieur
    -1.16
     Jefus
    -1.13
     $_"
    -1.11
     Anſ
    -1.08
    ^(@)
    -1.08
     Houſe
    -1.07
    POSITIVE LOGITS
    ,
    0.66
     in
    0.62
     O
    0.58
    ↵↵
    0.57
    ↵
    0.57
    .
    0.56
     ur
    0.55
    no
    0.54
     (
    0.53
    med
    0.53
    Act Density 0.025%

    No Known Activations