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

    Neuronpedia

    INDEX
    Explanations

    improve

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     myſelf
    -1.27
     pleaſure
    -1.25
     itſelf
    -1.21
     betweenstory
    -1.17
     themſelves
    -1.16
     Majefty
    -1.15
     himſelf
    -1.14
     Efq
    -1.13
     Jefus
    -1.13
     Monfieur
    -1.11
    POSITIVE LOGITS
     
    0.66
    <eos>
    0.60
     (
    0.60
    /
    0.59
     “
    0.58
     vers
    0.56
     l
    0.55
     ‘
    0.55
     '
    0.54
     on
    0.54
    Act Density 1.218%

    No Known Activations