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

    Neuronpedia

    INDEX
    Explanations

    also

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     itſelf
    -1.33
     myſelf
    -1.28
    存于互联网档案馆
    -1.21
     alſo
    -1.17
     themſelves
    -1.11
    NUMX
    -1.09
     ſhe
    -1.08
     photolibrary
    -1.05
     ſtate
    -1.05
     ſeveral
    -1.05
    POSITIVE LOGITS
    <eos>
    1.03
     manage
    0.57
     switch
    0.52
     to
    0.50
     pri
    0.48
     get
    0.47
     EconPapers
    0.46
     -
    0.46
    ok
    0.46
     V
    0.45
    Act Density 0.037%

    No Known Activations