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

    Neuronpedia

    INDEX
    Explanations

    citations and references

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     not
    0.77
     не
    0.75
     only
    0.73
     або
    0.68
     да
    0.67
     entirely
    0.67
     unpleasant
    0.67
     legs
    0.64
     halves
    0.63
    小数
    0.63
    POSITIVE LOGITS
     Institut
    0.93
    Institut
    0.89
    Xinhua
    0.85
     Fédération
    0.83
     李
    0.82
    itschrift
    0.81
     Націона
    0.80
    Istituto
    0.80
     日本
    0.79
     Institute
    0.78
    Act Density 0.001%

    No Known Activations