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

    Neuronpedia

    INDEX
    Explanations

    currency symbols

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (metadata
    -0.08
    (update
    -0.07
    (lang
    -0.07
    𝐲
    -0.07
    _supply
    -0.07
    (pf
    -0.07
     matches
    -0.06
     وإن
    -0.06
    setQuery
    -0.06
    (columns
    -0.06
    POSITIVE LOGITS
    ACS
    0.07
     Fear
    0.06
    义
    0.06
    $$$$
    0.06
     מחדש
    0.06
    middle
    0.06
    �
    0.06
     ست
    0.06
    alternative
    0.06
     BAT
    0.06
    Act Density 0.134%

    No Known Activations