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

    Neuronpedia

    INDEX
    Explanations

    expressions of uncertainty and complexity in information

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

    ambiguity and uncertainty

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    HasAnnotation
    -0.54
    AnimationsModule
    -0.46
    Aacute
    -0.39
    userdetails
    -0.38
    ularis
    -0.37
    estris
    -0.37
     recon
    -0.36
     rebo
    -0.36
    usercontent
    -0.35
    andre
    -0.35
    POSITIVE LOGITS
     uncertainty
    0.69
     uncertainties
    0.67
    SharedCtor
    0.63
    +#+#
    0.62
     Uncertainty
    0.61
     ambiguity
    0.60
     Uncertain
    0.59
    Uncertainty
    0.58
     disambiguazione
    0.57
     incertidumbre
    0.55
    Act Density 0.165%

    No Known Activations