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

    Neuronpedia

    INDEX
    Explanations

    decisive conjunctions and determiners

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    śród
    0.93
    𝚎
    0.92
     pratiquer
    0.91
    𝐪
    0.90
    стым
    0.90
    𝚊
    0.89
     direitos
    0.86
     dô
    0.84
    пол
    0.84
    𝚔
    0.84
    POSITIVE LOGITS
     \
    1.00
    (\\
    0.94
    ).
    0.91
    ),
    0.83
    )
    0.82
    .)
    0.81
    "),
    0.81
    (/\
    0.80
    (\
    0.79
    ).\\
    0.79
    Act Density 0.000%

    No Known Activations