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

    Neuronpedia

    INDEX
    Explanations

    by name

    np_acts-logits-general · gemini-2.5-flash-lite

    placeholders

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    0.62
    ,
    0.52
    -
    0.51
      
    0.50
    :
    0.48
     in
    0.48
     for
    0.47
     (
    0.46
     and
    0.46
    .
    0.45
    POSITIVE LOGITS
    <unused2020>
    0.46
    <unused50>
    0.42
    <unused1103>
    0.41
    اونلوډ
    0.40
    <unused95>
    0.40
    <unused25>
    0.40
    <unused73>
    0.40
    <unused22>
    0.39
    <unused66>
    0.39
    followlike
    0.38
    Act Density 0.216%

    No Known Activations