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

    Neuronpedia

    INDEX
    Explanations

    here are percentage

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Seals
    1.22
     لين
    1.11
     Bea
    1.09
     Boyle
    1.08
     sledge
    1.08
     скульп
    1.06
    лната
    1.05
    玥
    1.05
     seals
    1.05
    1.04
    POSITIVE LOGITS
    %
    1.88
     %
    1.74
    %,
    1.40
    %.
    1.31
     percent
    1.27
    %)
    1.27
    \%
    1.23
    Percent
    1.23
    ％
    1.22
    \%$
    1.22
    Act Density 0.558%

    No Known Activations