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

    Neuronpedia

    INDEX
    Explanations

    systems and their components

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    v
    0.52
    m
    0.51
    زين
    0.49
    能夠
    0.48
    兩種
    0.45
    猜测
    0.45
    bí
    0.44
    峄
    0.44
    浏览器
    0.44
    银行
    0.43
    POSITIVE LOGITS
     subsystem
    0.50
    QUIS
    0.49
     ☐
    0.49
    a
    0.46
     ↓
    0.46
     Subst
    0.46
     subst
    0.45
     subm
    0.45
    感覚
    0.45
    immunity
    0.45
    Act Density 0.000%

    No Known Activations