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

    Neuronpedia

    INDEX
    Explanations

    technical terms and phrases related to statistics and data analysis

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

    after certain base words

    np_acts-logits-general · gemini-2.0-flash

    technical termsexceptions, effects, corrections

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    SequentialGroup
    -0.76
    InvalidProtocol
    -0.61
    msford
    -0.59
    >",
    -0.59
     كومونز
    -0.58
     viewDidLoad
    -0.57
    DidLoad
    -0.56
     externi
    -0.54
    fromCharCode
    -0.53
    ágok
    -0.53
    POSITIVE LOGITS
     effect
    0.77
    AnchorStyles
    0.73
    enabled
    0.68
     effects
    0.66
     enabled
    0.65
     phenomenon
    0.64
     mechanism
    0.64
     Effect
    0.60
    InputBorder
    0.60
    inducing
    0.58
    Act Density 1.181%

    No Known Activations