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

    Neuronpedia

    INDEX
    Explanations

    list, continues, and breaks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    la
    0.47
    nas
    0.47
    november
    0.46
     व्हेल
    0.46
     харак
    0.45
    hydrogen
    0.45
    ke
    0.45
     Това
    0.44
     तिजारत
    0.44
    o
    0.44
    POSITIVE LOGITS
    EL
    0.44
     Liqu
    0.41
    }$\
    0.41
     Moris
    0.40
     hatta
    0.40
    の影響
    0.40
     trialComponents
    0.40
     fourth
    0.40
    KH
    0.40
    還有
    0.39
    Act Density 0.000%

    No Known Activations