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

    Neuronpedia

    INDEX
    Explanations

    Okay, let's break down

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ${\
    0.82
    ürt
    0.79
    upply
    0.79
    ರ್ಯ
    0.78
     FontSize
    0.76
    distan
    0.75
    ulfonic
    0.74
    "(
    0.73
     belirl
    0.71
     않았
    0.71
    POSITIVE LOGITS
    된
    0.87
    이
    0.80
    явление
    0.76
    되지
    0.76
     большим
    0.75
    Д
    0.75
     kolej
    0.75
     XMFLOAT
    0.73
    ใช้
    0.73
    ขอ
    0.73
    Act Density 0.187%

    No Known Activations