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

    Neuronpedia

    INDEX
    Explanations

    as

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    uuml
    -0.07
    ernetes
    -0.07
    ινη
    -0.06
    (Logger
    -0.06
    lín
    -0.06
     inputFile
    -0.06
     written
    -0.06
     revolutionary
    -0.06
    �
    -0.06
    Ｌ
    -0.06
    POSITIVE LOGITS
     as
    0.07
     AS
    0.07
    นะ
    0.07
     APIs
    0.07
    这么
    0.07
     inhab
    0.06
    as
    0.06
     подоб
    0.06
    —as
    0.06
    pizza
    0.06
    Act Density 0.021%

    No Known Activations