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

    Neuronpedia

    INDEX
    Explanations

    bring income

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     SafeArea
    0.54
    मार्
    0.53
     mistake
    0.50
     padlock
    0.50
    ็จ
    0.49
    마
    0.49
    戰
    0.49
    頭
    0.48
    偉
    0.48
    ោ
    0.47
    POSITIVE LOGITS
    ang
    0.57
    rifugal
    0.54
    around
    0.53
    ie
    0.52
    Be
    0.51
    elijke
    0.51
    ue
    0.50
    .
    0.50
    ara
    0.49
    <0x8F>
    0.49
    Act Density 0.000%

    No Known Activations