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

    Neuronpedia

    INDEX
    Explanations

    words and phrases that convey affirmations or assertions

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

    meaning/is/are/exists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    TagMode
    -0.67
    posedge
    -0.48
    iconque
    -0.47
    новништво
    -0.45
    IContainer
    -0.44
     Subsequently
    -0.44
    ScopeManager
    -0.44
    ulele
    -0.43
    principalTable
    -0.43
    OutOfRange
    -0.42
    POSITIVE LOGITS
    seamnă
    0.52
     ialah
    0.49
     là
    0.48
     adalah
    0.48
    upakan
    0.47
     Somos
    0.47
    isinstance
    0.45
     هي
    0.44
     являются
    0.44
     Là
    0.43
    Act Density 0.021%

    No Known Activations