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

    Neuronpedia

    INDEX
    Explanations

    ingredients and instructions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     kullanıcı
    0.54
     mundo
    0.51
     şark
    0.51
     presidente
    0.51
    音乐
    0.50
    8
    0.50
     alebo
    0.50
     sosyal
    0.49
     yapmak
    0.49
    นี้
    0.49
    POSITIVE LOGITS
    b
    0.58
    s
    0.57
    t
    0.54
    an
    0.52
    re
    0.52
    p
    0.52
    on
    0.51
    ad
    0.49
    d
    0.49
    q
    0.46
    Act Density 2.091%

    No Known Activations