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

    Neuronpedia

    INDEX
    Explanations

    across, surrounding, application

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ك
    0.66
    제목
    0.59
    䅐
    0.57
    屒
    0.56
    د
    0.56
    ام
    0.55
     ګرځ
    0.55
    انت
    0.55
    능
    0.54
    تقدم
    0.53
    POSITIVE LOGITS
     I
    0.63
    eel
    0.54
    EM
    0.52
    OL
    0.51
    ել
    0.48
     müs
    0.47
     can
    0.46
    0.46
     kej
    0.46
    OST
    0.45
    Act Density 0.000%

    No Known Activations