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

    Neuronpedia

    INDEX
    Explanations

    words ending in "ian" or related to programming

    oai_token-act-pair · gemini-2.0-flash

    ian

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ed
    -1.46
    ه
    -1.32
    es
    -1.32
    en
    -1.25
    a
    -1.23
    er
    -1.23
    м
    -1.12
    an
    -1.11
    e
    -1.09
    ing
    -1.03
    POSITIVE LOGITS
     Efq
    1.21
     Meksiku
    1.10
     Мексичка
    1.10
    <unused1>
    1.09
    <unused30>
    1.09
    <unused19>
    1.09
    <unused28>
    1.09
    <unused21>
    1.09
    <unused6>
    1.09
    <unused16>
    1.09
    Act Density 3.199%

    No Known Activations