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

    Neuronpedia

    INDEX
    Explanations

    Poe and faux

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ي
    0.79
    "
    0.73
    ر
    0.71
     Auth
    0.69
    i
    0.64
    కు
    0.63
    “
    0.63
    t
    0.62
    లో
    0.62
    du
    0.59
    POSITIVE LOGITS
    \},
    0.52
     ต้อง
    0.52
     बाधा
    0.52
     ダイヤモンド
    0.51
     فی
    0.50
     présente
    0.50
    ന്റ
    0.50
     도형
    0.50
     اپنی
    0.50
    uti
    0.49
    Act Density 0.000%

    No Known Activations