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

    Neuronpedia

    INDEX
    Explanations

    Markov Models transitions observations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     정리
    0.42
     ANOVA
    0.41
     domin
    0.39
     カー
    0.38
     NOL
    0.37
     herd
    0.37
    DOMContentLoaded
    0.36
     प्रभु
    0.36
     estratég
    0.36
    DMA
    0.35
    POSITIVE LOGITS
    transitions
    0.57
     Beob
    0.54
     Transitions
    0.53
    Transitions
    0.52
    Transition
    0.50
     Observation
    0.50
     transitions
    0.50
    觀察
    0.50
    transition
    0.48
     observation
    0.48
    Act Density 0.025%

    No Known Activations