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

    Neuronpedia

    INDEX
    Explanations

    function signatures and methods in programming code

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

    Result types and unsafe operations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     betweenstory
    -0.80
     للاسماء
    -0.74
    LookAnd
    -0.64
    transQ
    -0.60
    fromnode
    -0.58
    onAttach
    -0.54
    uxxxx
    -0.54
    PerformLayout
    -0.51
    ⓧ
    -0.50
    Datuak
    -0.49
    POSITIVE LOGITS
     a
    0.68
     an
    0.55
     henne
    0.49
     تضيفلها
    0.48
    thenReturn
    0.45
     unique
    0.44
    IsContent
    0.43
    alleros
    0.43
    HasColumnType
    0.43
     defaultstate
    0.43
    Act Density 0.004%

    No Known Activations