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

    Neuronpedia

    INDEX
    Explanations

    identify things

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    นี้
    0.94
    いた
    0.89
    و
    0.87
    up
    0.84
    न
    0.84
    います
    0.81
    in
    0.80
    いる
    0.79
    on
    0.79
    u
    0.79
    POSITIVE LOGITS
     rõ
    0.68
    𝑑
    0.68
    𝑧
    0.62
    iation
    0.60
    ాలు
    0.59
     மற்றும்
    0.59
     ένας
    0.59
     awọn
    0.57
     Shayari
    0.57
    SELECTOR
    0.57
    Act Density 0.697%

    No Known Activations