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

    Neuronpedia

    INDEX
    Explanations

    determinism and position

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    vertices
    0.43
     ისინი
    0.42
    笊
    0.41
    ველი
    0.41
    SearchResults
    0.39
    เว็บ
    0.39
    വർ
    0.38
     moulding
    0.38
    వర్
    0.38
    HDD
    0.37
    POSITIVE LOGITS
     került
    0.44
    Click
    0.42
     Pebble
    0.40
     Click
    0.39
    Tap
    0.38
     Tap
    0.37
     repaired
    0.36
    <0xA4>
    0.36
    RUNTIME
    0.36
     also
    0.36
    Act Density 0.001%

    No Known Activations