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

    Neuronpedia

    INDEX
    Explanations

    modal verbs indicating possibility or ability combined with negations

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

    must go

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ValueStyle
    -0.47
    SourceChecksum
    -0.46
    gangenheit
    -0.44
    engesch
    -0.42
    optionalTypeArgs
    -0.40
     המצ
    -0.39
    новниш
    -0.39
     myself
    -0.39
    튿
    -0.39
     fac
    -0.38
    POSITIVE LOGITS
    __":
    0.47
    modelBuilder
    0.42
     فريبيس
    0.41
    __":
    0.39
     womb
    0.39
     AssemblyProduct
    0.39
    __':
    0.38
    abstractmethod
    0.38
    featureID
    0.38
     EconPapers
    0.37
    Act Density 0.256%

    No Known Activations