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

    Neuronpedia

    INDEX
    Explanations

    verbs followed by common words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     स्टूडेंट
    0.53
     శ
    0.47
     파
    0.47
     직
    0.46
     étroites
    0.45
     ঠিক
    0.45
     dejó
    0.45
    striatis
    0.44
     보니
    0.44
     tecido
    0.44
    POSITIVE LOGITS
    lun
    0.43
    以便
    0.42
    كن
    0.42
    RNN
    0.41
     Zn
    0.41
     quản
    0.40
    \(
    0.40
    arz
    0.39
    andered
    0.39
     moderator
    0.38
    Act Density 0.000%

    No Known Activations