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

    Neuronpedia

    INDEX
    Explanations

    javascript code snippets, particularly unit tests using 'expect'

    oai_token-act-pair · gemini-2.0-flash

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     itſelf
    -0.87
    ſelf
    -0.86
     Majefty
    -0.81
     Jefus
    -0.80
     himſelf
    -0.79
     reaſon
    -0.77
     poffible
    -0.75
     Monfieur
    -0.74
     Theſe
    -0.74
     ſtre
    -0.73
    POSITIVE LOGITS
     standing
    0.45
    תי
    0.42
     I
    0.41
     
    0.41
    ngdoc
    0.41
    bright
    0.36
     stands
    0.36
     (
    0.36
     stood
    0.35
    ætte
    0.35
    Act Density 5.737%

    No Known Activations