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

    Neuronpedia

    INDEX
    Explanations

    linguistic structures related to searching and locating

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

    seeking out and tracking

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    exc
    -0.39
     acting
    -0.37
    Exc
    -0.36
     corporate
    -0.36
     performing
    -0.35
     ASP
    -0.34
     gesch
    -0.34
    Allow
    -0.34
     houden
    -0.34
     biological
    -0.34
    POSITIVE LOGITS
    findpost
    0.81
     resourceCulture
    0.60
    ftagPool
    0.59
    ConstraintMaker
    0.58
    delwed
    0.57
     дописавши
    0.56
     finder
    0.55
     Seeker
    0.55
     FIND
    0.54
    LookAnd
    0.54
    Act Density 0.126%

    No Known Activations