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

    Neuronpedia

    INDEX
    Explanations

    following prompts or structured text

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ！”
    0.68
    azol
    0.66
     Büh
    0.64
     Smol
    0.60
     absol
    0.59
    av
    0.58
    !”,
    0.58
     players
    0.58
    撿
    0.57
    殯
    0.56
    POSITIVE LOGITS
    >
    1.91
     >
    1.77
    >>
    1.64
     >>
    1.59
    >;
    1.52
    >*
    1.48
    ]>
    1.47
    ?>
    1.47
    >\
    1.44
    >>>
    1.43
    Act Density 0.111%

    No Known Activations