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

    Neuronpedia

    INDEX
    Explanations

    Fountain pens

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ों
    0.68
    дә
    0.63
    ק
    0.59
    ான
    0.58
    ی
    0.54
    ים
    0.54
     μία
    0.54
    ır
    0.52
    าว
    0.52
    ب
    0.52
    POSITIVE LOGITS
    Phone
    0.57
    Window
    0.53
    지만
    0.53
     \
    0.52
    Index
    0.52
    Message
    0.52
    em
    0.51
    History
    0.51
    Collection
    0.51
    _
    0.51
    Act Density 0.000%

    No Known Activations