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

    Neuronpedia

    INDEX
    Explanations

    references to baseline measurements and their associations in scientific experiments

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

    baseline and natural conditions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    exitRule
    -0.63
    sizeCache
    -0.60
    complexContent
    -0.60
     autorytatywna
    -0.58
    RegressionTest
    -0.57
    WebElementEntity
    -0.57
    postIndex
    -0.53
     Signalez
    -0.51
     continúas
    -0.50
    ConstraintMaker
    -0.50
    POSITIVE LOGITS
     pre
    0.52
     initial
    0.40
     natural
    0.40
     pré
    0.39
    日常
    0.37
     naturali
    0.36
     regular
    0.36
     maintained
    0.36
     naturale
    0.35
     rotina
    0.35
    Act Density 0.276%

    No Known Activations