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

    Neuronpedia

    INDEX
    Explanations

    references to important concepts and emerging types of tools, particularly in scientific contexts

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

    increase or increased magnitude

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     operation
    -0.27
     judges
    -0.26
     reductase
    -0.26
     Kont
    -0.26
     compulsion
    -0.24
    EXCLUSIVE
    -0.24
     dzies
    -0.23
     provocation
    -0.23
     gard
    -0.22
     trompe
    -0.22
    POSITIVE LOGITS
     فريبيس
    0.88
    adaptiveStyles
    0.82
     الحره
    0.74
    RegressionTest
    0.70
    AnchorTagHelper
    0.66
    Билгалдахарш
    0.65
    AsUp
    0.65
    IntoConstraints
    0.65
     nahilalakip
    0.64
    ConstraintMaker
    0.63
    Act Density 0.042%

    No Known Activations