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

    Neuronpedia

    INDEX
    Explanations

    terms related to identification and recognition

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

    identifiable information

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ariot
    -0.47
     الرخصة
    -0.42
     therapy
    -0.41
    ureux
    -0.41
    اضي
    -0.40
    ץ
    -0.40
     treatment
    -0.39
    Ex
    -0.39
     proposed
    -0.39
    RequestMethod
    -0.39
    POSITIVE LOGITS
     recognizable
    1.85
     recognisable
    1.75
     identifiable
    1.55
     discernible
    1.11
     distinguishable
    0.98
     unmistakable
    0.96
     unrecogn
    0.94
     perceptible
    0.91
     noticeable
    0.91
     detectable
    0.88
    Act Density 0.009%

    No Known Activations