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

    Neuronpedia

    INDEX
    Explanations

    lists of Spanish words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     splashing
    0.42
     bowling
    0.40
    পান
    0.38
     обязанности
    0.38
    উর
    0.38
    alag
    0.38
    ្ឋ
    0.37
     ছি
    0.37
    جهه
    0.37
    IPOP
    0.36
    POSITIVE LOGITS
    ars
    0.39
    solar
    0.39
    同一个
    0.39
    क्स
    0.39
     Reverse
    0.38
     используется
    0.38
     like
    0.38
     becomes
    0.38
     SP
    0.38
     stack
    0.38
    Act Density 0.000%

    No Known Activations