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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating transition or questions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     支持
    0.57
     dSample
    0.56
     qualités
    0.55
    。</
    0.54
     useCustom
    0.54
     wodurch
    0.54
     模型
    0.54
    ൮
    0.53
    براير
    0.52
     frases
    0.52
    POSITIVE LOGITS
    s
    0.62
    M
    0.57
    T
    0.56
    t
    0.55
    U
    0.52
      
    0.51
    0
    0.50
    is
    0.50
    ↵↵
    0.49
    c
    0.49
    Act Density 0.000%

    No Known Activations