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

    Neuronpedia

    INDEX
    Explanations

    instances of specific programming or markup conventions

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

    setminus,CONTENT,del,sub,XXX

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ***!
    -0.46
    AutoField
    -0.44
     تضيفلها
    -0.36
    hésite
    -0.35
    OGND
    -0.34
     refusé
    -0.34
    writeHead
    -0.34
     považ
    -0.33
     jopa
    -0.33
     connues
    -0.33
    POSITIVE LOGITS
    WebElementEntity
    0.76
     betweenstory
    0.74
    cyon
    0.66
     Numerade
    0.66
    RegressionTest
    0.65
    __
    0.65
     INSEE
    0.62
    djangoproject
    0.61
    AISSEE
    0.60
     Geiſt
    0.60
    Act Density 0.011%

    No Known Activations