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

    Neuronpedia

    INDEX
    Explanations

    different shapes and forms of discs and stripes

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

    shapes like discs, sheets, or stripes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ’
    -0.39
    '
    -0.39
     and
    -0.38
     The
    -0.38
     the
    -0.38
    *
    -0.38
      
    -0.36
    1
    -0.36
    .
    -0.36
    ↵
    -0.36
    POSITIVE LOGITS
    parsedMessage
    1.10
     betweenstory
    1.08
     $_(
    1.01
    makeConstraints
    0.95
     faſt
    0.93
     queſta
    0.93
    ########.
    0.92
     transfieras
    0.90
    <unused28>
    0.89
    <unused52>
    0.89
    Act Density 0.110%

    No Known Activations