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

    Neuronpedia

    INDEX
    Explanations

    listing items or alternatives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    0.60
    that
    0.44
    I
    0.42
     toate
    0.42
     which
    0.38
     that
    0.38
     hali
    0.38
     sesi
    0.37
    ר
    0.36
    ่
    0.36
    POSITIVE LOGITS
    其他
    0.43
     tecnología
    0.39
     ఇతర
    0.38
     τότε
    0.37
    vět
    0.37
    citep
    0.36
     políticas
    0.36
    <unused2026>
    0.36
     чёр
    0.36
     política
    0.35
    Act Density 0.714%

    No Known Activations