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

    Neuronpedia

    INDEX
    Explanations

    zero

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ွက်
    0.65
     forte
    0.64
     apasion
    0.63
     Northwest
    0.62
     प्रकोष्ठ
    0.61
     Galaxy
    0.61
     남
    0.61
     Spanish
    0.59
    杏
    0.59
     ínt
    0.59
    POSITIVE LOGITS
     zero
    4.06
    zero
    3.57
     Zero
    3.54
     ZERO
    3.51
    Zero
    3.50
     zéro
    3.28
     cero
    3.26
    ZERO
    3.10
     zeros
    3.06
    ゼロ
    3.03
    Act Density 0.533%

    No Known Activations