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

    Neuronpedia

    INDEX
    Explanations

    statements about medical or scientific advancements, particularly in relation to treatments

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

    Deals with byte buffers and lengths

    np_acts-logits-general · gemini-2.0-flash

    bytes per datapoint

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Coal
    -0.47
     Fran
    -0.46
     Bot
    -0.44
    tev
    -0.44
     fac
    -0.44
     objectForKey
    -0.44
    JsonValue
    -0.44
     Jane
    -0.43
     Mine
    -0.43
     Clark
    -0.43
    POSITIVE LOGITS
     bytes
    1.01
     buffer
    0.88
     Bytes
    0.88
    byte
    0.87
     byte
    0.86
    Bytes
    0.86
     ByteBuffer
    0.82
    bytes
    0.80
     Buffer
    0.78
    BYTES
    0.77
    Act Density 0.927%

    No Known Activations