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

    Neuronpedia

    INDEX
    Explanations

    post-apocalyptic settings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ен
    0.59
    jar
    0.58
    ایش
    0.58
    ной
    0.57
     V
    0.57
     пыта
    0.57
    αν
    0.56
     चिह्न
    0.55
     wasteful
    0.55
    రిగి
    0.54
    POSITIVE LOGITS
    is
    1.01
    }$,
    0.78
    }
    0.75
     těchto
    0.71
    в
    0.71
    }$
    0.70
    sdf
    0.68
     einiger
    0.66
     této
    0.64
    fica
    0.63
    Act Density 0.001%

    No Known Activations