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

    Neuronpedia

    INDEX
    Explanations

    phrases that denote key characteristics or indicators of specific biological or legal concepts

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

    hallmark of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     sky
    -0.34
     spray
    -0.34
     Sky
    -0.34
     fry
    -0.34
     plastiques
    -0.33
    erschiedene
    -0.33
     cras
    -0.33
     race
    -0.33
     sort
    -0.32
     sper
    -0.31
    POSITIVE LOGITS
     hallmark
    1.88
     Hallmark
    1.64
    marks
    0.82
     AssemblyCompany
    0.81
     signature
    0.81
    characteristic
    0.81
     trademark
    0.79
     characteristic
    0.78
     landmark
    0.78
     Characteristic
    0.77
    Act Density 0.007%

    No Known Activations