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

    Neuronpedia

    INDEX
    Explanations

    math, programming, and scientific terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Tân
    0.71
    Otra
    0.70
    PPh
    0.68
     padrões
    0.68
     órdenes
    0.65
     sepol
    0.64
     presume
    0.64
    Popup
    0.63
     Wrist
    0.60
    Records
    0.60
    POSITIVE LOGITS
     and
    0.94
    および
    0.87
    และ
    0.85
    且
    0.82
     και
    0.79
     आणि
    0.78
    并且
    0.77
    而且
    0.76
     và
    0.76
     וכ
    0.76
    Act Density 0.000%

    No Known Activations