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

    Neuronpedia

    INDEX
    Explanations

    references to personal experiences and relationships

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

    favorite team, especially pandas

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    IntoConstraints
    -0.69
    ########.
    -0.66
    DeleteBehavior
    -0.64
     ब्रेकडाउन
    -0.61
    Personendaten
    -0.58
    richTextPanel
    -0.57
     resourceCulture
    -0.57
     صوتيه
    -0.56
    exitRule
    -0.55
    tetés
    -0.55
    POSITIVE LOGITS
    ros
    0.39
    omethane
    0.37
    ябре
    0.36
    stan
    0.36
    OrBuilder
    0.33
    ChildIndex
    0.31
     род
    0.30
     emer
    0.30
     fair
    0.30
     fon
    0.30
    Act Density 0.115%

    No Known Activations