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

    Neuronpedia

    INDEX
    Explanations

    -

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    生き
    -0.07
     Angels
    -0.06
    arians
    -0.06
    urus
    -0.06
     Elder
    -0.06
    _Find
    -0.06
     Carson
    -0.06
    dog
    -0.06
     Baz
    -0.06
     Advance
    -0.06
    POSITIVE LOGITS
     alte
    0.08
    トル
    0.07
     reassure
    0.07
    although
    0.06
    yte
    0.06
    ète
    0.06
    ूब
    0.06
     bzw
    0.06
     modele
    0.06
    径
    0.06
    Act Density 0.001%

    No Known Activations