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

    Neuronpedia

    INDEX
    Explanations

    the words "behavior" or "behaviour"

    oai_token-act-pair · gemini-2.0-flash

    behavior

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     behavior
    -3.09
     behaviour
    -2.94
     Behavior
    -2.81
    behavior
    -2.70
     Behaviour
    -2.64
    Behavior
    -2.53
    behaviour
    -2.48
     BEHAVIOR
    -2.41
     behaviors
    -2.41
    Behaviour
    -2.31
    POSITIVE LOGITS
     TextAppearance
    0.68
    PerformLayout
    0.67
     resourceCulture
    0.63
    ]")]
    0.60
    WEBPACK
    0.57
    enumi
    0.56
    ArgsConstructor
    0.55
     picada
    0.53
     ReactDOM
    0.52
    šanai
    0.52
    Act Density 0.542%

    No Known Activations