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
     Ukrain
    -0.08
     Friendship
    -0.08
    _student
    -0.07
     Deep
    -0.07
     Reed
    -0.07
     Desmond
    -0.07
     Odyssey
    -0.06
    ımlar
    -0.06
    Inverse
    -0.06
     Riv
    -0.06
    POSITIVE LOGITS
     있어서
    0.06
     selfish
    0.06
     aktuellen
    0.06
     permissions
    0.06
     indexes
    0.06
     pos
    0.05
     Поэтому
    0.05
     concede
    0.05
     hallmark
    0.05
    ΙΑΣ
    0.05
    Act Density 0.002%

    No Known Activations