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

    Neuronpedia

    INDEX
    Explanations

    elements of code or programming language syntax

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

    Two-letter prefixes in words

    np_acts-logits-general · gemini-2.0-flash

    beginnings of words and abbreviations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    assemblée
    -0.50
    exécution
    -0.49
    adhé
    -0.47
    esercito
    -0.46
    étape
    -0.45
    élaboration
    -0.44
    ambassade
    -0.43
    atmosphère
    -0.42
    équipement
    -0.42
    extrême
    -0.41
    POSITIVE LOGITS
     betweenstory
    0.47
    isometric
    0.43
    ankle
    0.40
    ivory
    0.40
    ene
    0.39
    erek
    0.38
    ️
    0.38
    anmar
    0.38
    ThroughAttribute
    0.38
    idol
    0.38
    Act Density 3.362%

    No Known Activations