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

    Neuronpedia

    INDEX
    Explanations

    trickiest parts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <unused2118>
    0.64
     Goodwin
    0.51
     inexplic
    0.50
    ]")
    0.49
     excused
    0.49
    “)
    0.48
    螓
    0.48
    )"))
    0.47
    めて
    0.47
     pitiful
    0.47
    POSITIVE LOGITS
     http
    0.67
    ämm
    0.59
     Essay
    0.56
     https
    0.54
     www
    0.53
    ier
    0.53
     Apakah
    0.52
     процессе
    0.52
     آیا
    0.51
     contador
    0.51
    Act Density 0.000%

    No Known Activations