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

    Neuronpedia

    INDEX
    Explanations

    cautions and recommendations related to safety and proper procedure

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

    pay attention or be careful

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    StructEnd
    -0.45
    المناصب
    -0.44
     apud
    -0.42
     betweenstory
    -0.41
     Normdatei
    -0.37
     épaules
    -0.37
    blurRadius
    -0.36
    ultati
    -0.36
     colored
    -0.36
     CanadaChoose
    -0.36
    POSITIVE LOGITS
     tránh
    0.43
    enschappelijke
    0.42
    ":[{
    0.42
    følgelig
    0.42
     careful
    0.42
     disponibilités
    0.41
     recognise
    0.41
    VersionUID
    0.41
    ficient
    0.40
     prévoir
    0.40
    Act Density 0.024%

    No Known Activations