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

    Neuronpedia

    INDEX
    Explanations

    more detailed information

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    とりあえず
    0.39
    首先
    0.38
    왠
    0.37
    ரும்
    0.36
    preconnect
    0.35
     كده
    0.35
    無需
    0.35
    ಿಲ್ಲ
    0.35
    స్త్ర
    0.35
    ியோ
    0.34
    POSITIVE LOGITS
     detailed
    2.47
     detal
    2.22
    Detailed
    2.17
     detail
    2.16
    詳細
    2.16
     Detailed
    2.16
    详细
    2.14
     подроб
    2.14
    detailed
    2.13
     details
    2.11
    Act Density 0.099%

    No Known Activations