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

    Neuronpedia

    INDEX
    Explanations

    political speculation and wrongdoing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    很多
    0.48
    ü
    0.47
    良い
    0.46
     poteva
    0.45
    ע
    0.45
    ъ
    0.44
    os
    0.42
    га
    0.42
     buvo
    0.42
     měla
    0.42
    POSITIVE LOGITS
    0.68
     of
    0.61
    the
    0.52
     the
    0.50
     l
    0.46
     wrongdoing
    0.46
     on
    0.46
     Cambridge
    0.44
     political
    0.41
     civilization
    0.41
    Act Density 0.003%

    No Known Activations