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

    Neuronpedia

    INDEX
    Explanations

    types

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     hầu
    -0.06
    ieber
    -0.06
     legalization
    -0.06
    (dict
    -0.06
    baru
    -0.06
    -menu
    -0.06
    ederation
    -0.06
    -san
    -0.06
    assert
    -0.06
     اص
    -0.06
    POSITIVE LOGITS
     housed
    0.07
     ↵    ↵
    0.06
     honeymoon
    0.06
    722
    0.06
     pornos
    0.06
     parent
    0.06
     irq
    0.06
    validated
    0.06
     můžete
    0.06
    victim
    0.06
    Act Density 0.000%

    No Known Activations