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

    Neuronpedia

    INDEX
    Explanations

    actions related to self-harm or suicidal behavior

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

    jumping or falling

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    اریخ
    -0.43
     صوتيه
    -0.41
    IVEREF
    -0.39
    houding
    -0.39
     tensão
    -0.38
     silenced
    -0.35
     siir
    -0.34
    ❹
    -0.34
     avanzada
    -0.34
     pressão
    -0.34
    POSITIVE LOGITS
     defaultstate
    0.62
    jump
    0.62
     Jump
    0.62
     suicide
    0.60
     jump
    0.60
    Jump
    0.60
     JUMP
    0.57
     jumping
    0.57
     drowning
    0.55
    Tembelea
    0.55
    Act Density 0.067%

    No Known Activations