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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "the"

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

    navigating system locations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    InjectAttribute
    -0.65
     ब्रेकडाउन
    -0.59
     otomatig
    -0.56
    تقاوى
    -0.55
    RegressionTest
    -0.53
     ModelExpression
    -0.52
    GraphicsUnit
    -0.51
    UrlResolution
    -0.50
    elemField
    -0.50
     Numerade
    -0.49
    POSITIVE LOGITS
     directory
    0.43
     pasted
    0.40
    conversation
    0.39
     panneau
    0.39
    directions
    0.38
     Directory
    0.38
    Desc
    0.36
     conversation
    0.36
     flags
    0.36
     chat
    0.35
    Act Density 0.045%

    No Known Activations