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

    Neuronpedia

    INDEX
    Explanations

    jailbreaking

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ដៃ
    0.45
    uterine
    0.45
     ভারতীয়
    0.43
    ઝ
    0.43
    ാൽ
    0.43
    InfoPlistPath
    0.43
    されました
    0.42
     sıcak
    0.42
    梸
    0.42
    onnées
    0.42
    POSITIVE LOGITS
    }\
    0.42
    (
    0.42
    D
    0.40
    }}(
    0.40
    */
    0.39
    Mar
    0.38
     preview
    0.38
    >(</
    0.38
    }}(\
    0.38
    Weekly
    0.38
    Act Density 0.001%

    No Known Activations