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

    Neuronpedia

    INDEX
    Explanations

    phrases and terms related to correctness and identification in a quiz or test context

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

    correct identification and accuracy

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    }}:
    -0.34
    bkz
    -0.34
    VersionUID
    -0.32
    Dipl
    -0.32
     posibil
    -0.32
    makedirs
    -0.32
    cdnjs
    -0.31
    Mitte
    -0.31
     Motta
    -0.31
    êques
    -0.31
    POSITIVE LOGITS
    Jereo
    0.56
    writeFieldEnd
    0.54
     kysy
    0.52
    SharedDtor
    0.52
     EconPapers
    0.49
    WriteTagHelper
    0.48
     ✭✭
    0.47
     correctly
    0.47
    IsContent
    0.46
    олові
    0.46
    Act Density 0.028%

    No Known Activations