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

    Neuronpedia

    INDEX
    Explanations

    programming terms related to user interface components and their management

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

    Code-related keywords or identifiers

    np_acts-logits-general · gemini-2.0-flash

    code identifiers and assignments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    う
    -0.31
     Grand
    -0.31
    RRect
    -0.30
    ec
    -0.29
    か
    -0.28
     Pued
    -0.27
    CreateMap
    -0.27
     hosting
    -0.27
    bat
    -0.27
     trans
    -0.26
    POSITIVE LOGITS
    ſelves
    0.81
     queſta
    0.79
    parsedMessage
    0.76
    <unused8>
    0.72
    <unused28>
    0.72
    <unused16>
    0.72
    <unused41>
    0.72
    <unused52>
    0.72
    <unused3>
    0.71
    <unused14>
    0.71
    Act Density 0.186%

    No Known Activations