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

    Neuronpedia

    INDEX
    Explanations

    thinking and considering possibilities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Viewport
    0.44
    または
    0.43
    ת
    0.43
     Gotham
    0.43
    فير
    0.42
     feces
    0.41
    をご覧
    0.40
     Kristen
    0.40
     recipients
    0.39
    িলা
    0.38
    POSITIVE LOGITS
    $/.
    0.47
     coloquei
    0.46
    parse
    0.46
     पण
    0.46
     είναι
    0.46
    ̀nh
    0.46
    介紹
    0.45
     ça
    0.45
    ocols
    0.45
    思路
    0.45
    Act Density 0.000%

    No Known Activations