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

    Neuronpedia

    INDEX
    Explanations

    not or no

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     никакого
    0.43
     asla
    0.40
    从来
    0.39
    ueil
    0.39
     geen
    0.38
     никогда
    0.36
     nikdy
    0.36
     žád
    0.36
    没有任何
    0.36
     गर्नु
    0.35
    POSITIVE LOGITS
     not
    2.27
    not
    2.03
    Not
    2.02
     Not
    1.91
     όχι
    1.40
     NOT
    1.36
    NOT
    1.30
     नॉट
    1.20
    不仅
    1.20
    不僅
    1.19
    Act Density 0.103%

    No Known Activations