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

    Neuronpedia

    INDEX
    Explanations

    proper nouns, specifically names of places and people

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

    Two- or three-letter prefixes

    np_acts-logits-general · gemini-2.0-flash

    proper names or compound words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     journées
    -0.51
     Offisielt
    -0.50
     Maske
    -0.49
     Tasche
    -0.48
     hierbas
    -0.48
     very
    -0.47
     Ferne
    -0.46
     Leinwand
    -0.46
     Handwerk
    -0.46
     Alianza
    -0.46
    POSITIVE LOGITS
    iſen
    0.70
    adaptiveStyles
    0.63
     Vac
    0.62
     yym
    0.60
     doInBackground
    0.59
    itsubishi
    0.58
     Lan
    0.58
     Vib
    0.58
    attutto
    0.57
     Squ
    0.57
    Act Density 1.090%

    No Known Activations