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

    Neuronpedia

    INDEX
    Explanations

    usage of the word "use" in various contexts

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

    uses such as

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Ä
    -0.34
     vors
    -0.31
    第
    -0.30
     besten
    -0.29
     thereafter
    -0.27
    ター
    -0.27
    хіво
    -0.27
    デ
    -0.26
     Derfor
    -0.26
     Echt
    -0.25
    POSITIVE LOGITS
    OGND
    0.82
    CppMethod
    0.80
     zoude
    0.80
    NameInMap
    0.72
     للاسماء
    0.71
    [@BOS@]
    0.70
    <unused74>
    0.70
    <unused41>
    0.69
    <unused8>
    0.69
    <unused3>
    0.69
    Act Density 0.000%

    No Known Activations