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

    Neuronpedia

    INDEX
    Explanations

    ThinkPad and Transformer models

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ۰
    1.33
    j
    1.33
    ال
    1.22
    ত্র
    1.21
    körper
    1.20
    させる
    1.20
    ようになりました
    1.20
    ট
    1.19
     hợp
    1.19
    mUserManager
    1.17
    POSITIVE LOGITS
    }$&
    1.37
    }$
    1.29
    ated
    1.21
    }\}$
    1.21
     bijection
    1.19
     porcelain
    1.16
     clutter
    1.15
    leetcode
    1.11
    +}$
    1.11
     been
    1.11
    Act Density 0.001%

    No Known Activations