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

    Neuronpedia

    INDEX
    Explanations

    aspects related to choices, examples, and specific claims in discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    numbers and specific words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    كويكب
    -0.47
     jspb
    -0.42
    IBOutlet
    -0.41
    ="@+
    -0.39
     IBOutlet
    -0.38
     GALERÍA
    -0.38
    ArrowToggle
    -0.37
     nakalista
    -0.36
    ConstraintMaker
    -0.35
    Général
    -0.35
    POSITIVE LOGITS
     незавершена
    0.64
     '\\;'
    0.59
     AssemblyCulture
    0.51
     someone
    0.50
     esimer
    0.49
    someone
    0.47
     example
    0.47
    цездатний
    0.47
    Smarty
    0.47
    niz
    0.46
    Act Density 0.069%

    No Known Activations