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

    Neuronpedia

    INDEX
    Explanations

    comparison of things

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     דר
    0.41
    呑
    0.41
    ्रू
    0.38
    OW
    0.38
     meningkatkan
    0.38
     ח
    0.38
    ٤
    0.37
     соціа
    0.37
    ブ
    0.37
     woon
    0.36
    POSITIVE LOGITS
    ার্থীর
    0.46
     Camry
    0.45
     devoted
    0.43
     motorists
    0.43
     depender
    0.43
     Carlisle
    0.42
     opponents
    0.41
    mittedly
    0.41
     Camaro
    0.41
    මාන්
    0.41
    Act Density 0.000%

    No Known Activations