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

    Neuronpedia

    INDEX
    Explanations

    expressions of desire and needs

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

    what they want

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     dimentic
    -0.43
    PostBack
    -0.43
    كويكب
    -0.40
    haupt
    -0.40
    ANEOUS
    -0.40
    führung
    -0.40
    ACLE
    -0.40
    RegressionTest
    -0.38
     Momente
    -0.38
     PeEnEo
    -0.38
    POSITIVE LOGITS
    帖最后由
    0.50
    IntoConstraints
    0.46
     برانيه
    0.45
     незавершена
    0.45
    makeConstraints
    0.44
     Wikimedijinoj
    0.43
    PreferredItem
    0.42
     Initialized
    0.42
     flex
    0.41
     öns
    0.41
    Act Density 0.084%

    No Known Activations