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

    Neuronpedia

    INDEX
    Explanations

    explanation, covering

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     striking
    0.49
    特点
    0.48
     vuoden
    0.46
     aparentemente
    0.46
     Although
    0.45
     সমস্যা
    0.45
    实际上
    0.44
    根据
    0.44
     stunning
    0.44
    ↵
    0.43
    POSITIVE LOGITS
     perspici
    0.62
    nails
    0.60
     webinars
    0.60
     QSOs
    0.59
     CSK
    0.59
    ⋯
    0.58
    𒋛
    0.58
    arrerol
    0.58
    ਾਰ
    0.57
     ........
    0.57
    Act Density 0.308%

    No Known Activations