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

    Neuronpedia

    INDEX
    Explanations

    specific sequences and patterns in actions and outcomes

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

    turning or landing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     CURIAM
    -0.55
    arashtra
    -0.52
    ﹧
    -0.50
    ffindor
    -0.50
    FieldOffsetTable
    -0.50
    dshaw
    -0.49
    Proportion
    -0.48
     Proportion
    -0.47
    oneg
    -0.47
    wellen
    -0.47
    POSITIVE LOGITS
    +#+#
    0.49
    SharedCtor
    0.47
    Архівовано
    0.41
     previa
    0.39
    $_['
    0.38
    sizeCache
    0.38
    EndInit
    0.35
    AndEndTag
    0.35
    FormTagHelper
    0.34
    DeleteBehavior
    0.34
    Act Density 0.002%

    No Known Activations