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

    Neuronpedia

    INDEX
    Explanations

    code and programming context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    း
    1.25
     eclipsed
    1.22
    rme
    1.14
    rmi
    1.11
    adə
    1.09
     ulcerative
    1.08
    קים
    1.07
    rotic
    1.07
    رة
    1.06
    <unused372>
    1.06
    POSITIVE LOGITS
    y
    1.06
     እንዲሁም
    0.84
    }")
    0.84
    ва
    0.83
    ર
    0.83
    assert
    0.82
    }"/>
    0.80
    م
    0.78
     നിറ
    0.77
    containing
    0.77
    Act Density 0.000%

    No Known Activations