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

    Neuronpedia

    INDEX
    Explanations

    list, array, dictionary

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    정
    0.46
    West
    0.41
    from
    0.41
    ভাগ্য
    0.40
    হীন
    0.40
    Establish
    0.39
    Ｂ
    0.39
    Name
    0.38
    The
    0.38
    량이
    0.37
    POSITIVE LOGITS
     ṣ
    0.45
     zusätzlich
    0.42
     myös
    0.41
     också
    0.41
    摖
    0.41
     แต่
    0.41
    而非
    0.40
     dédié
    0.40
     plutôt
    0.39
     adaptés
    0.39
    Act Density 0.007%

    No Known Activations