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

    Neuronpedia

    INDEX
    Explanations

    numbers after phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ✨
    0.86
     (\
    0.85
     ($\
    0.81
     (
    0.81
     👇
    0.77
     🎉
    0.75
     आम्ही
    0.75
     (“
    0.73
    \"\
    0.73
     🙏
    0.73
    POSITIVE LOGITS
    <unused538>
    0.95
    <unused937>
    0.94
    <unused289>
    0.89
    <unused958>
    0.89
    <unused696>
    0.89
    <unused972>
    0.86
    <unused1050>
    0.85
    0.85
    <unused704>
    0.85
    <unused1851>
    0.85
    Act Density 0.016%

    No Known Activations