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

    Neuronpedia

    INDEX
    Explanations

    numbers and counts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    1
    0.51
    0.50
    -
    0.45
    0
    0.41
     l
    0.39
    (
    0.39
    %
    0.38
     m
    0.38
    ,
    0.37
     p
    0.36
    POSITIVE LOGITS
    mités
    0.44
    <unused1828>
    0.44
    निश्
    0.43
     ذریع
    0.42
    हमी
    0.42
    <unused2058>
    0.42
     Evam
    0.41
     INKA
    0.41
    <unused340>
    0.41
     CommandCenter
    0.40
    Act Density 0.001%

    No Known Activations