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

    Neuronpedia

    INDEX
    Explanations

    capturing groups and complex processes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     otras
    0.41
     다른
    0.41
    ليزية
    0.40
    ্বিক
    0.38
    と言
    0.38
    binary
    0.37
    Mira
    0.36
     literalmente
    0.36
     কিভাবে
    0.35
     outras
    0.35
    POSITIVE LOGITS
    delivered
    0.39
    scapes
    0.39
     —,
    0.38
     levied
    0.38
     livré
    0.38
     delivered
    0.37
     summer
    0.36
    saturation
    0.36
    writ
    0.36
     nominations
    0.36
    Act Density 0.005%

    No Known Activations