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

    Neuronpedia

    INDEX
    Explanations

    cautions and warnings related to health and medication usage

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

    that indicate avoidance or prohibition

    np_acts-logits-general · gemini-2.0-flash

    avoid or excessive actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     виправивши
    -0.71
    følgelig
    -0.69
    الإنجليزية
    -0.60
    HideFlags
    -0.60
    anggil
    -0.59
     manageable
    -0.58
     fairest
    -0.58
    帖最后由
    -0.57
    lysm
    -0.57
    ArgumentParser
    -0.56
    POSITIVE LOGITS
     excessively
    0.87
     слишком
    0.87
     terlalu
    0.87
     too
    0.82
     unsupervised
    0.80
     troppo
    0.79
     excessive
    0.79
     overly
    0.79
     demasi
    0.78
    too
    0.77
    Act Density 0.447%

    No Known Activations