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

    Neuronpedia

    INDEX
    Explanations

    percentage ranges and numerical sequences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    共产
    0.65
    法规
    0.61
    共产党
    0.59
    公开
    0.55
     kullanım
    0.54
     ব্যবহার
    0.53
     kullanıcı
    0.52
     procédures
    0.51
    产业
    0.50
     appareils
    0.50
    POSITIVE LOGITS
     slightly
    0.79
     slight
    0.74
     range
    0.71
    range
    0.68
     transitional
    0.68
     marginally
    0.66
    slightly
    0.66
     nearby
    0.65
     contiguous
    0.65
    adjacent
    0.64
    Act Density 0.151%

    No Known Activations