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

    Neuronpedia

    INDEX
    Explanations

    aspects of concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    산
    0.57
    하는
    0.48
    산을
    0.47
     인증
    0.46
     기능을
    0.46
     capacidad
    0.45
    动作
    0.45
     batería
    0.45
     biến
    0.44
     바꾸
    0.44
    POSITIVE LOGITS
    m
    0.58
    tr
    0.55
    t
    0.53
    v
    0.50
    faq
    0.50
    l
    0.50
    ti
    0.49
    it
    0.49
    k
    0.47
    gent
    0.46
    Act Density 0.001%

    No Known Activations