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

    Neuronpedia

    INDEX
    Explanations

    terms related to behavioral changes and therapies

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

    behavior changes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Económica
    -0.54
     Nacionales
    -0.46
     Dritte
    -0.45
    Parcelize
    -0.43
     Frankrijk
    -0.43
    Vezi
    -0.42
     komplet
    -0.41
     mine
    -0.41
     Munro
    -0.41
     missed
    -0.41
    POSITIVE LOGITS
     Behavior
    1.22
     behavior
    1.20
    behavior
    1.16
    Behavior
    1.14
     BEHAVIOR
    1.13
     Behaviour
    1.10
    behaviour
    1.09
     behaviour
    1.09
    Behaviour
    1.02
     Behaviors
    1.02
    Act Density 0.032%

    No Known Activations