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

    Neuronpedia

    INDEX
    Explanations

    every day

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Ін
    1.12
     மிக
    0.98
     Suche
    0.96
    Downward
    0.92
    𝙚
    0.92
     +
    0.91
     કપ
    0.90
    ств
    0.90
     але
    0.89
    รู
    0.87
    POSITIVE LOGITS
     breadth
    1.47
    ع
    1.35
     permissible
    1.33
     subalgebra
    1.24
     shelter
    1.23
     inauguration
    1.23
     ordained
    1.22
     depth
    1.22
     seater
    1.22
    cathode
    1.22
    Act Density 0.000%

    No Known Activations