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

    Neuronpedia

    INDEX
    Explanations

    conversational phrases related to personal desires and aspirations

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

    knows what he wants

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    parsedMessage
    -0.49
     للاسماء
    -0.45
    ativement
    -0.40
    gonic
    -0.35
    providedIn
    -0.35
    setupUi
    -0.35
    nodoc
    -0.35
     jeugd
    -0.34
    DOCTYPE
    -0.34
     defaultstate
    -0.33
    POSITIVE LOGITS
     للمعارف
    0.53
    kloped
    0.52
    LTRB
    0.46
     clou
    0.44
    Wipe
    0.44
     sweats
    0.44
    IsContent
    0.44
    Occurrences
    0.43
    つもり
    0.43
     MyBatis
    0.43
    Act Density 0.041%

    No Known Activations