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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     طب
    -0.06
     spéc
    -0.06
     determines
    -0.06
     learns
    -0.06
    19
    -0.06
     Sophie
    -0.06
    .JSONException
    -0.06
     Kem
    -0.06
    ))↵↵↵
    -0.06
     obtained
    -0.06
    POSITIVE LOGITS
     Луч
    0.08
    UTOR
    0.07
    인데
    0.07
    cerer
    0.07
     Checked
    0.06
     ama
    0.06
    ดำเน
    0.06
    uciones
    0.06
    énom
    0.06
    :&
    0.06
    Act Density 0.010%

    No Known Activations