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

    Neuronpedia

    INDEX
    Explanations

    significantly hurts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    갬
    1.27
    勳
    1.25
    مجھے
    1.24
    िक
    1.24
     deiner
    1.19
    Мак
    1.19
    izont
    1.19
    ૨
    1.18
    вшихся
    1.18
     kunt
    1.17
    POSITIVE LOGITS
     warning
    1.09
    s
    1.05
     要
    1.01
    Corollary
    1.00
     तो
    0.97
    view
    0.97
     view
    0.94
     लिए
    0.92
    houd
    0.90
     यह
    0.89
    Act Density 0.000%

    No Known Activations