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

    Neuronpedia

    INDEX
    Explanations

    expressions of personal experiences and emotions

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

    admitting to questions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    FunctionFlags
    -0.62
     HasFactory
    -0.61
     '\\;'
    -0.57
     typelib
    -0.56
    ronpa
    -0.55
    tvguidetime
    -0.53
    Попис
    -0.52
    󠁴
    -0.51
     الرياضيه
    -0.51
     estekak
    -0.51
    POSITIVE LOGITS
     verg
    0.38
     ChromeDriver
    0.31
    stylers
    0.28
     MutableLiveData
    0.27
    SizeMode
    0.26
    UIControlState
    0.26
    lapsingToolbar
    0.26
    addPreferredGap
    0.26
    $_['
    0.25
     Rik
    0.25
    Act Density 0.025%

    No Known Activations