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

    Neuronpedia

    INDEX
    Explanations

    terms related to educational resources and community engagement

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

    specific terms or entities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ThemeData
    -0.32
    fail
    -0.31
     fail
    -0.30
     fat
    -0.30
    -
    -0.29
     Fatty
    -0.29
    ISSUES
    -0.29
    iv
    -0.28
    ]].
    -0.28
     onları
    -0.28
    POSITIVE LOGITS
     Reſ
    0.78
     purpoſe
    0.75
    Xna
    0.75
     pleaſure
    0.75
     anſ
    0.70
     ſche
    0.68
     ſal
    0.66
     Anſ
    0.66
     juſ
    0.65
     ſtand
    0.65
    Act Density 0.030%

    No Known Activations