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

    Neuronpedia

    INDEX
    Explanations

    words related to scientific discoveries and health topics

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

    verb followed by noun/phrase

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     is
    -0.37
     may
    -0.33
     that
    -0.32
     was
    -0.31
     it
    -0.30
     그
    -0.29
     until
    -0.29
     there
    -0.29
     should
    -0.28
     might
    -0.28
    POSITIVE LOGITS
    ftagPool
    0.95
     transfieras
    0.92
    IsMutable
    0.91
    IndentedString
    0.88
    sizeCache
    0.85
    bootstrapcdn
    0.85
     propOrder
    0.84
    uxxxx
    0.82
     <>",
    0.81
     $_"
    0.80
    Act Density 0.010%

    No Known Activations