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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .meta
    -0.27
    ä¸ĢèĦļ
    -0.26
    akit
    -0.26
    è°ħ
    -0.24
    vertise
    -0.24
     erg
    -0.24
    /meta
    -0.23
     zwarte
    -0.23
    weather
    -0.23
    LEAR
    -0.23
    POSITIVE LOGITS
    被æī§è¡Į
    0.29
     Torres
    0.27
    è¦ģä¹Ī
    0.26
    产ä¸ļåĮĸ
    0.26
    atori
    0.25
    toBeDefined
    0.24
    eln
    0.24
     Parkway
    0.24
    .raise
    0.24
    年人
    0.24
    Act Density 0.013%

    No Known Activations