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

    Neuronpedia

    INDEX
    Explanations

    terms related to testing and assessment processes

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

    test case

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     fä
    -0.40
    edict
    -0.37
    Captor
    -0.36
    $_['
    -0.35
    seits
    -0.35
    bottom
    -0.35
    makeConstraints
    -0.34
     companhia
    -0.34
    endphp
    -0.34
    strans
    -0.33
    POSITIVE LOGITS
    =$?
    0.52
    体操
    0.52
    Hauptartikel
    0.50
    BeginContext
    0.49
    IUrlHelper
    0.47
    parsedMessage
    0.46
    RectangleBorder
    0.45
    iastical
    0.45
     typelib
    0.44
     afer
    0.44
    Act Density 0.223%

    No Known Activations