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

    Neuronpedia

    INDEX
    Explanations

    common word pairs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     anaemia
    0.41
    曰
    0.40
    緊
    0.40
     उक्त
    0.40
    Aph
    0.39
    吖
    0.39
    クーポン
    0.39
    টেও
    0.39
    ويه
    0.38
     வட்டம்
    0.38
    POSITIVE LOGITS
    drinks
    0.42
    .»
    0.38
    །
    0.38
    ্
    0.38
    imani
    0.37
    लेन
    0.37
    rans
    0.36
    »
    0.36
    :.
    0.36
    icmp
    0.36
    Act Density 0.000%

    No Known Activations