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

    Neuronpedia

    INDEX
    Explanations

    closing punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     mediterranean
    0.39
     bilirubin
    0.39
     hoti
    0.38
    scrire
    0.38
     މަ
    0.37
    ളം
    0.37
     brilli
    0.36
    setzungen
    0.36
     mediterr
    0.36
    дования
    0.35
    POSITIVE LOGITS
    .]
    0.44
    ].
    0.41
    ↵↵
    0.40
    周
    0.40
    }.
    0.40
    .)
    0.39
    .'
    0.38
    '.
    0.38
    ).
    0.38
    .".
    0.38
    Act Density 0.009%

    No Known Activations