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

    Neuronpedia

    INDEX
    Explanations

    programming-related constructs and identifiers in code

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

    Code, properties, and system calls

    np_acts-logits-general · gemini-2.0-flash

    code elements like identifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     kasarigan
    -0.47
    AndroidJUnit
    -0.29
    UseVisualStyle
    -0.29
     afgelopen
    -0.28
     pinulongan
    -0.28
     rigue
    -0.28
     perpé
    -0.27
     familières
    -0.26
     našich
    -0.26
    Datuak
    -0.26
    POSITIVE LOGITS
     Fantasia
    0.75
    <unused41>
    0.72
    <unused23>
    0.72
    [@BOS@]
    0.72
    bildtitel
    0.72
    <unused51>
    0.72
    <unused74>
    0.72
    <unused52>
    0.72
    <unused14>
    0.72
    <unused28>
    0.72
    Act Density 0.365%

    No Known Activations