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

    Neuronpedia

    INDEX
    Explanations

    Sh + ifting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     sh
    0.75
    sh
    0.61
    Sh
    0.54
    ખ
    0.49
     Sh
    0.48
     sha
    0.48
     শ
    0.46
     श
    0.46
     SH
    0.46
    SH
    0.46
    POSITIVE LOGITS
     pedi
    0.43
    ᔭ
    0.41
     homeowner
    0.40
     Cute
    0.40
    汔
    0.40
    (:,
    0.39
     Chromebook
    0.39
     MSE
    0.39
     MRT
    0.39
     Ayurvedic
    0.39
    Act Density 0.004%

    No Known Activations