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

    Neuronpedia

    INDEX
    Explanations

    parts, in, son

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     তিনিই
    0.48
     रोक
    0.48
    状態で
    0.43
    רג
    0.42
    Jumlah
    0.41
     tables
    0.41
     בכל
    0.41
    场所
    0.40
     Palmas
    0.39
    樀
    0.39
    POSITIVE LOGITS
    রু
    0.49
     expecting
    0.48
    expect
    0.46
    openweathermap
    0.45
     ước
    0.44
     modernized
    0.44
    imely
    0.43
    áférés
    0.43
    imori
    0.42
     revolutionized
    0.42
    Act Density 0.011%

    No Known Activations