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

    Neuronpedia

    INDEX
    Explanations

    expert systems

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    grunt
    0.54
    动力
    0.49
     production
    0.49
    适应
    0.49
     Multiply
    0.49
     مُ
    0.48
     Fermi
    0.47
     खुले
    0.46
     яго
    0.46
    剡
    0.46
    POSITIVE LOGITS
    5
    0.63
    스
    0.61
    った
    0.60
    म
    0.59
    은
    0.59
    6
    0.58
    یت
    0.58
    7
    0.58
    ني
    0.57
    வ
    0.57
    Act Density 0.000%

    No Known Activations