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

    Neuronpedia

    INDEX
    Explanations

    phrasing that indicates ongoing evaluation or uncertainty regarding a condition or hypothesis

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

    remains to be elucidated

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    GeneratedMessage
    -0.53
     estekak
    -0.53
    MLLoader
    -0.52
    CppMethod
    -0.51
    BufferException
    -0.50
     للمعارف
    -0.50
    AsUp
    -0.50
    OGND
    -0.49
    SourceChecksum
    -0.48
     magasiner
    -0.48
    POSITIVE LOGITS
    脚注の使い方
    0.50
     remaining
    0.43
     remains
    0.43
     urme
    0.41
    setdefault
    0.40
    NotImplemented
    0.40
    artifactId
    0.40
     miljoen
    0.39
    remaining
    0.37
    quela
    0.36
    Act Density 0.005%

    No Known Activations