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

    Neuronpedia

    INDEX
    Explanations

    terms related to data types, particularly short integers

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

    short specifier

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    DotNetBar
    -0.51
     maxSize
    -0.45
     cytoplasm
    -0.44
    gettyimages
    -0.43
    demy
    -0.42
     Cay
    -0.41
     utafitiHapana
    -0.40
     DOCUMENTS
    -0.39
    cua
    -0.39
     való
    -0.39
    POSITIVE LOGITS
    Short
    2.23
    short
    2.19
     Short
    2.16
     short
    2.00
     SHORT
    1.99
    SHORT
    1.94
    短
    1.57
     fhort
    1.44
    Shorts
    1.40
    shorts
    1.38
    Act Density 0.016%

    No Known Activations