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

    Neuronpedia

    INDEX
    Explanations

    references to significant historical events or figures

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

    Adjectives describing characters or portrayals

    np_acts-logits-general · gemini-2.0-flash

    endearing, sympathetic, lovable characters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    webElementXpaths
    -0.61
    ształ
    -0.55
    Bodies
    -0.54
     céu
    -0.53
     Bodies
    -0.51
    tvguidetime
    -0.50
     étan
    -0.49
     ahor
    -0.49
     bewer
    -0.49
     aimez
    -0.49
    POSITIVE LOGITS
     fles
    0.85
     sympathetic
    0.84
     lik
    0.80
     portrayed
    0.79
     believable
    0.78
     portrayal
    0.70
     conflicted
    0.70
     endearing
    0.70
     lovable
    0.69
    GEBURTSDATUM
    0.68
    Act Density 0.214%

    No Known Activations