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

    Neuronpedia

    INDEX
    Explanations

    files and messages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    et
    1.05
    e
    1.04
    ون
    0.99
    ⊔
    0.96
     tutur
    0.92
    স
    0.91
     ВС
    0.88
    y
    0.87
    (),
    0.86
    ल्फी
    0.86
    POSITIVE LOGITS
    polyfill
    1.01
    𝗜
    0.96
     Produk
    0.93
    𝗔
    0.92
    }$\\
    0.91
    ї
    0.91
    }$&
    0.89
    𝗢
    0.89
     reverts
    0.89
    টো
    0.89
    Act Density 0.225%

    No Known Activations