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

    Neuronpedia

    INDEX
    Explanations

    words and phrases within legal documents used when providing attestations

    oai_token-act-pair · gemini-2.0-flash

    legal documents

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    awtextra
    -0.94
    NUMX
    -0.94
    CompleteListener
    -0.83
    felves
    -0.82
     nakalista
    -0.82
     poffible
    -0.81
    ſelf
    -0.81
     виправивши
    -0.81
     otomatig
    -0.80
    noinspection
    -0.80
    POSITIVE LOGITS
     A
    0.47
     (
    0.45
    .
    0.43
     far
    0.41
     ca
    0.39
     -
    0.39
     
    0.39
     fär
    0.38
    ~
    0.37
     and
    0.37
    Act Density 1.460%

    No Known Activations