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

    Neuronpedia

    INDEX
    Explanations

    **NOTE:** (parenthetical notes)

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     বাঙ্গালার
    0.98
    U
    0.91
    ैंड
    0.91
     учены
    0.91
    ة
    0.88
    ής
    0.84
    MING
    0.84
    museum
    0.83
    ০০
    0.83
    મુ
    0.83
    POSITIVE LOGITS
    .
    1.13
    /
    1.09
    ).
    1.04
    -
    0.92
    ;
    0.85
    ),
    0.84
    .”
    0.79
     bona
    0.79
     dated
    0.77
    .}
    0.75
    Act Density 0.123%

    No Known Activations