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

    Neuronpedia

    INDEX
    Explanations

    occurrences of phrases that indicate arrival or interaction points

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

    stop by

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    IntoConstraints
    -0.60
     médicaux
    -0.59
     judiciaire
    -0.56
     fallu
    -0.56
     abstrato
    -0.56
     étoient
    -0.54
     avoient
    -0.53
    Erreferentziak
    -0.50
     chrétien
    -0.49
     electrico
    -0.48
    POSITIVE LOGITS
     visit
    0.81
     Visit
    0.72
    visit
    0.72
    Visit
    0.71
     visits
    0.69
     visited
    0.66
     VISIT
    0.64
    visite
    0.63
    VISIT
    0.63
     Visited
    0.62
    Act Density 0.007%

    No Known Activations