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

    Neuronpedia

    INDEX
    Explanations

    the words "being" and "having"

    oai_token-act-pair · gemini-2.0-flash

    states of existence

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     فريبيس
    -1.36
     Efq
    -1.29
     myſelf
    -1.28
     незавершена
    -1.26
     Monfieur
    -1.23
     houſe
    -1.23
    AndEndTag
    -1.23
     Houſe
    -1.22
    Portály
    -1.20
     Majefty
    -1.20
    POSITIVE LOGITS
    H
    0.52
    Id
    0.51
     v
    0.51
     im
    0.51
    V
    0.49
     w
    0.48
     des
    0.48
    l
    0.48
    Are
    0.47
     om
    0.47
    Act Density 0.305%

    No Known Activations