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

    Neuronpedia

    INDEX
    Explanations

    and pronoun

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Bogotá
    0.49
    r
    0.49
     Lieut
    0.49
     IntPtr
    0.47
     Bicycle
    0.46
     Đầu
    0.45
    ျ
    0.45
    ía
    0.44
     الأمير
    0.44
     Ultra
    0.43
    POSITIVE LOGITS
    werte
    0.59
    ンダー
    0.58
    İZ
    0.57
    ﾓ
    0.54
    PA
    0.53
    वर्क
    0.53
    ძლიათ
    0.52
     dersimizde
    0.51
     biasing
    0.51
    .",
    0.50
    Act Density 0.000%

    No Known Activations