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

    Neuronpedia

    INDEX
    Explanations

    tasks and roles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Oklahoma
    0.46
    enido
    0.44
    ንሽ
    0.43
    ιά
    0.43
    siehe
    0.42
    🐔
    0.42
    🚐
    0.42
     維尼
    0.42
     spineItem
    0.41
    ,(((
    0.41
    POSITIVE LOGITS
     و
    0.51
     и
    0.51
     CV
    0.46
     and
    0.44
     JET
    0.44
     convinc
    0.43
    صب
    0.43
    وفي
    0.42
     AND
    0.41
    stroke
    0.41
    Act Density 0.001%

    No Known Activations