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

    Neuronpedia

    INDEX
    Explanations

    comes down to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     wave
    0.46
     seu
    0.45
     downward
    0.42
     okazji
    0.41
     tentu
    0.40
     sank
    0.40
     során
    0.39
    ownt
    0.39
     વખતે
    0.38
     Down
    0.38
    POSITIVE LOGITS
    Brass
    0.63
    brass
    0.58
     Brass
    0.57
     brass
    0.55
    basic
    0.50
    Dollars
    0.48
     기본
    0.45
    dollars
    0.44
     बुनियादी
    0.43
     dependence
    0.43
    Act Density 0.003%

    No Known Activations