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

    Neuronpedia

    INDEX
    Explanations

    references to lists or items, such as figures, links, or documents

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

    references and citations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     beginnetje
    -0.60
    RefNanny
    -0.59
    WebServlet
    -0.58
    tonsoft
    -0.56
     الرياضيه
    -0.54
    MigrationBuilder
    -0.54
    IVEREF
    -0.54
    setupUi
    -0.52
    DebuggerNonUser
    -0.49
    хьтан
    -0.49
    POSITIVE LOGITS
    <u>
    0.50
    <strong>
    0.46
     accelerating
    0.42
     оригіналу
    0.42
    ELAND
    0.39
     surla
    0.39
    <b>
    0.39
     accelerate
    0.38
     통해
    0.38
     refuse
    0.37
    Act Density 0.385%

    No Known Activations