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

    Neuronpedia

    INDEX
    Explanations

    quantitative and comparative language expressing amounts or quantities

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

    Prepositions and numbers

    np_acts-logits-general · gemini-2.0-flash

    numbers followed by time units

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    出版年
    -0.45
     дописавши
    -0.42
     Gegenteil
    -0.42
     Audiodateien
    -0.37
    ViewFeatures
    -0.36
     Inseln
    -0.36
     nélkül
    -0.36
     esterni
    -0.36
    createStatement
    -0.35
     Widerspruch
    -0.34
    POSITIVE LOGITS
     AssemblyProduct
    0.52
    chromatic
    0.51
    alli
    0.51
    хьтан
    0.51
    cotta
    0.50
    nitive
    0.49
    woor
    0.49
    setFocusable
    0.49
    ELIA
    0.49
     Mill
    0.48
    Act Density 0.522%

    No Known Activations