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

    Neuronpedia

    INDEX
    Explanations

    abortion rights

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     bardziej
    0.46
     conséquences
    0.44
     أ
    0.44
     χωρίς
    0.41
     more
    0.40
     collège
    0.40
    ادية
    0.39
    يف
    0.39
     rağmen
    0.38
     DEI
    0.38
    POSITIVE LOGITS
    ҷ
    0.43
     చక్క
    0.42
    -'].
    0.41
    -
    0.41
    URLConnection
    0.41
    пита
    0.40
    合った
    0.39
    口味
    0.39
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.38
    蝴
    0.38
    Act Density 0.003%

    No Known Activations