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

    Neuronpedia

    INDEX
    Explanations

    patterns that match specific regular expressions or syntactical structures

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

    regex matched number `B >`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     activator
    -0.51
    ']
    -0.51
    ）』
    -0.51
    '))
    -0.50
    ")
    -0.49
    QRST
    -0.49
    ++)
    -0.49
    ]}$
    -0.48
     access
    -0.48
    ')
    -0.48
    POSITIVE LOGITS
     /\.(
    0.74
     AssemblyVersion
    0.73
     kasarigan
    0.72
    CloseOperation
    0.71
    .*
    0.70
    .-.
    0.66
    ("."
    0.66
     للاسماء
    0.63
    .-(
    0.63
     ['./
    0.63
    Act Density 0.061%

    No Known Activations