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

    Neuronpedia

    INDEX
    Explanations

    with followed by descriptors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    م
    0.57
    z
    0.52
    v
    0.49
    a
    0.49
    ق
    0.47
    Task
    0.47
    j
    0.47
    is
    0.46
    l
    0.46
    from
    0.46
    POSITIVE LOGITS
    )}')
    0.49
    िरिक्स
    0.47
    പ്പെടുന്നു
    0.46
     McIntyre
    0.44
     プ
    0.44
    DBObject
    0.44
     pribli
    0.43
     radiotherapy
    0.43
     počíta
    0.43
     horrendous
    0.43
    Act Density 0.000%

    No Known Activations