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

    Neuronpedia

    INDEX
    Explanations

    references to violent or criminal acts

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

    Body parts following "to" and "the"

    np_acts-logits-general · gemini-2.0-flash

    body parts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     незавершена
    -0.61
     العنوان
    -0.56
     lenker
    -0.52
    biór
    -0.46
     때문
    -0.45
    rsiniz
    -0.43
     myö
    -0.42
    rustic
    -0.42
    himovic
    -0.41
    wakili
    -0.41
    POSITIVE LOGITS
     eyes
    1.78
     feet
    1.57
     ears
    1.56
     legs
    1.51
     hands
    1.50
     fingers
    1.47
     lips
    1.42
     mouth
    1.42
     arms
    1.42
     nose
    1.39
    Act Density 0.617%

    No Known Activations