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

    Neuronpedia

    INDEX
    Explanations

    Galois theory / nitric oxide / gpio

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    その
    1.60
    𝘵
    1.59
     într
    1.56
    ‍या
    1.55
    𝘰
    1.54
    во
    1.51
     dre
    1.47
     berkel
    1.46
     sust
    1.46
    CIO
    1.45
    POSITIVE LOGITS
    на
    1.91
     относятся
    1.89
    लिये
    1.78
    悱
    1.78
    तुरंग
    1.77
    SecurityMarks
    1.75
     slammed
    1.75
     बबलू
    1.72
    dirs
    1.69
     bothered
    1.68
    Act Density 0.000%

    No Known Activations