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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     freshwater
    -0.06
    िजन
    -0.06
     voluntary
    -0.06
     parasites
    -0.06
     کسب
    -0.06
     Remed
    -0.06
    ChangeListener
    -0.06
    creds
    -0.06
     Modifications
    -0.06
    Assistant
    -0.06
    POSITIVE LOGITS
     sä
    0.07
     tương
    0.07
    UCCEEDED
    0.07
     صح
    0.06
    ﾘ
    0.06
    ัตร
    0.06
     interrupt
    0.06
    VS
    0.06
     ([
    0.06
    ************************
    0.06
    Act Density 0.006%

    No Known Activations