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

    Neuronpedia

    INDEX
    Explanations

    references to albums, licenses, and proteins

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

    "Album" or "LICENSE" (all caps)

    np_acts-logits-general · gemini-2.0-flash

    Album, LICENSE, Flamingo

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    er
    -0.73
    </em>
    -0.69
    areth
    -0.67
    ce
    -0.65
    ch
    -0.61
    “
    -0.60
    h
    -0.59
    be
    -0.58
    בל
    -0.58
     
    -0.57
    POSITIVE LOGITS
     itſelf
    1.13
     Majefty
    1.12
     pleaſure
    1.09
     NSObject
    1.07
     Monfieur
    1.02
    providedIn
    0.97
     Jefus
    0.97
     $_"
    0.95
     myſelf
    0.95
    viedo
    0.94
    Act Density 0.687%

    No Known Activations