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

    Neuronpedia

    INDEX
    Explanations

    \mathbb{R}

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ～！
    -0.93
    を
    -0.88
     Ravenna
    -0.84
    aturing
    -0.81
    хваты
    -0.79
    ！(
    -0.78
     clara
    -0.78
     dijual
    -0.78
    zonej
    -0.78
     sudut
    -0.77
    POSITIVE LOGITS
    ళ
    0.92
     เขา
    0.91
     RECOMM
    0.87
    czyki
    0.84
     EXPLANATION
    0.84
     Brings
    0.82
     ориги
    0.82
    0.82
    のでしょう
    0.81
    though
    0.80
    Act Density 0.009%

    No Known Activations