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

    Neuronpedia

    INDEX
    Explanations

    geographical names and administrative regions

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

    Letter/number followed by specific punctuation

    np_acts-logits-general · gemini-2.0-flash

    'w' and 'cm' followed by locations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ThroughAttribute
    -0.79
     Roskov
    -0.76
     дописавши
    -0.67
     nahilalakip
    -0.67
    protoimpl
    -0.65
     متعلقه
    -0.62
     CreateTagHelper
    -0.59
     kaarangay
    -0.58
     مشين
    -0.57
    antaine
    -0.57
    POSITIVE LOGITS
     Additions
    0.44
     Needles
    0.43
     smar
    0.43
     bpy
    0.42
     suche
    0.42
    Jîn
    0.42
     communautés
    0.42
    ग्री
    0.42
     päivä
    0.41
    suche
    0.40
    Act Density 0.004%

    No Known Activations