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

    Neuronpedia

    INDEX
    Explanations

    model's response marker

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    فك
    0.79
    笔者
    0.77
     யோ
    0.76
     topic
    0.72
    topic
    0.68
    Topic
    0.66
    Awesome
    0.66
     débat
    0.65
     yada
    0.65
     debat
    0.64
    POSITIVE LOGITS
     роль
    0.82
    olone
    0.80
    ኋ
    0.78
    rizioni
    0.77
    }
    0.76
    িয়াম
    0.75
    сква
    0.74
     Streets
    0.74
     जितनी
    0.73
    厘米
    0.73
    Act Density 0.101%

    No Known Activations