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

    Neuronpedia

    INDEX
    Explanations

    questions that inquire about unusual or humorous situations

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

    "I have", "You have"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    MessageOf
    -0.63
    存于互联网档案馆
    -0.54
    flink
    -0.49
    KommentareTeilen
    -0.49
     saites
    -0.48
    WEBPACK
    -0.48
    ----</
    -0.45
    Crom
    -0.45
    يميديا
    -0.45
    tagHelperRunner
    -0.45
    POSITIVE LOGITS
     Comprometido
    0.33
     Audiodateien
    0.32
    illigen
    0.31
    ⋙
    0.30
    eraard
    0.30
     bo
    0.29
     hook
    0.29
     choir
    0.29
     Bo
    0.29
     really
    0.29
    Act Density 0.032%

    No Known Activations