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

    Neuronpedia

    INDEX
    Explanations

    ```

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    𝐓
    0.96
     and
    0.93
    رى
    0.93
     altitudes
    0.86
    larından
    0.86
     enveloped
    0.86
    hitung
    0.84
    ಯಲ್ಲಿ
    0.81
    களை
    0.76
    கள்
    0.75
    POSITIVE LOGITS
    ir
    1.69
    ak
    1.55
    ia
    1.39
    り
    1.39
    ே
    1.38
    та
    1.35
    am
    1.34
    ু
    1.34
    ون
    1.31
    ad
    1.30
    Act Density 0.011%

    No Known Activations