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

    Neuronpedia

    INDEX
    Explanations

    ads, function, surname, model

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    o
    0.47
    á
    0.43
    onden
    0.41
    ply
    0.40
    。「
    0.40
    ă
    0.40
    wirkung
    0.39
    ō
    0.39
    ons
    0.39
     /ˈ
    0.39
    POSITIVE LOGITS
     such
    0.50
     any
    0.49
     зависи
    0.46
     comenc
    0.45
     salads
    0.44
     ו
    0.43
    మా
    0.41
     जिसमे
    0.41
    కు
    0.41
     camels
    0.40
    Act Density 2.810%

    No Known Activations