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

    Neuronpedia

    INDEX
    Explanations

    references to institutional or organizational contexts and codes

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

    canola cans apples imports

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ly
    -0.44
    y
    -0.39
    ob
    -0.36
    ing
    -0.34
     ...
    -0.32
     rapid
    -0.32
    ↵↵
    -0.31
    d
    -0.31
     …
    -0.31
    <em>
    -0.31
    POSITIVE LOGITS
    IntoConstraints
    0.98
     Cana
    0.91
    ⟬
    0.90
     Cans
    0.86
     canes
    0.83
    Cana
    0.82
    parsedMessage
    0.81
    Canna
    0.79
     Audiodateien
    0.77
     Canucks
    0.76
    Act Density 0.025%

    No Known Activations