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

    Neuronpedia

    INDEX
    Explanations

    but though

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    xcodep
    0.56
    ципа
    0.54
     clockRadius
    0.54
    ன்ஹீ
    0.52
    '}}
    0.52
     arrondies
    0.50
    actionBarTab
    0.50
     значения
    0.50
    xgb
    0.49
     pertumbuhan
    0.48
    POSITIVE LOGITS
     can
    0.61
     if
    0.59
    .
    0.57
     at
    0.55
     doesn
    0.54
     in
    0.52
    inst
    0.51
    e
    0.51
     Brazilian
    0.50
     Can
    0.50
    Act Density 0.001%

    No Known Activations