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

    Neuronpedia

    INDEX
    Explanations

    proper nouns and specific geographical or historical place names

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

    Uncommon words or tokens

    np_acts-logits-general · gemini-2.0-flash

    geographic place names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     pieles
    -0.38
     Geheimnis
    -0.37
    @[+][
    -0.37
     Vortrag
    -0.37
     sonunda
    -0.36
     Haltung
    -0.36
    polazione
    -0.34
    Enviado
    -0.34
     ustedes
    -0.33
    receta
    -0.33
    POSITIVE LOGITS
     kasarigan
    0.59
     lateinit
    0.57
     Majefty
    0.56
     WebApplication
    0.56
     Seeder
    0.52
    fjspx
    0.51
    AppCompat
    0.51
    0.50
    ᅠ
    0.50
    TemporalType
    0.49
    Act Density 0.462%

    No Known Activations