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

    Neuronpedia

    INDEX
    Explanations

    explaining reasons

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    нов
    0.47
    세계
    0.43
     Instruments
    0.43
    atibus
    0.41
    ార్లు
    0.39
    eworld
    0.39
    世界
    0.39
    В
    0.39
    Gay
    0.38
    <0xC2>
    0.38
    POSITIVE LOGITS
     menikah
    0.42
     निघा
    0.41
    uncertain
    0.40
    قطه
    0.40
     tred
    0.39
     certainty
    0.38
     asistir
    0.38
     uncertainties
    0.38
    是一名
    0.38
     residential
    0.38
    Act Density 0.001%

    No Known Activations