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

    Neuronpedia

    INDEX
    Explanations

    JSON-like data structure representations and elements

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

    Data table formatting or key-value pairs

    np_acts-logits-general · gemini-2.0-flash

    JSON keys with values

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    parsedMessage
    -0.89
    ⟬
    -0.86
    RegressionTest
    -0.84
    expandindo
    -0.81
    featureID
    -0.81
    transQ
    -0.79
    TagMode
    -0.77
    inWeight
    -0.76
     betweenstory
    -0.74
    GraphicsUnit
    -0.73
    POSITIVE LOGITS
     
    0.38
     roll
    0.29
     rolled
    0.29
    «
    0.29
     rest
    0.29
     Corp
    0.29
     spare
    0.28
     Cap
    0.28
    vânt
    0.28
    <tbody>
    0.27
    Act Density 1.374%

    No Known Activations