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

    Neuronpedia

    INDEX
    Explanations

    references to specific entities, proper nouns, or defined subjects within the text

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

    digits, punctuation, and symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Verhält
    -0.42
     śmier
    -0.33
     télécharge
    -0.31
     neumáticos
    -0.30
     dingen
    -0.30
     migrantes
    -0.30
     vectorielle
    -0.30
    จุด
    -0.30
     comportamiento
    -0.28
     estructuras
    -0.28
    POSITIVE LOGITS
     kasarigan
    0.67
     onCreateView
    0.65
    0.63
     surla
    0.63
    𓇠
    0.61
    齮
    0.61
    pexpr
    0.61
    ="@+
    0.60
     zuſammen
    0.60
    ThroughAttribute
    0.60
    Act Density 1.206%

    No Known Activations