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

    Neuronpedia

    INDEX
    Explanations

    access to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     t
    1.13
    般的
    1.04
     laat
    1.02
    ્સ
    1.02
    這裡
    1.01
    不错
    0.97
    ،
    0.96
    뭐
    0.96
     jsme
    0.94
    ，
    0.94
    POSITIVE LOGITS
    ند
    1.52
    and
    1.30
     remoto
    1.29
     unwarrant
    1.28
    ant
    1.27
    enos
    1.26
    ون
    1.21
    pineapple
    1.21
    tır
    1.20
     intraven
    1.20
    Act Density 0.087%

    No Known Activations