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

    Neuronpedia

    INDEX
    Explanations

    themes of emotional release and personal growth

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

    Negative emotions or self-sabotaging thoughts

    np_acts-logits-general · gemini-2.0-flash

    negative feelings and self-criticism

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ViewFeatures
    -0.61
    endforeach
    -0.60
    ﾟ)
    -0.59
    łbym
    -0.58
     sẻ
    -0.56
     Roskov
    -0.56
    Hentet
    -0.55
    SuppressLint
    -0.54
     estekak
    -0.53
    tagens
    -0.53
    POSITIVE LOGITS
     sabo
    0.78
     blaming
    0.73
     toxic
    0.72
     guilt
    0.72
     perfection
    0.71
     self
    0.67
     shame
    0.67
     destructive
    0.67
     negative
    0.66
     unhealthy
    0.66
    Act Density 0.326%

    No Known Activations