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

    Neuronpedia

    INDEX
    Explanations

    huge range or variety

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     standalone
    0.64
     onboarding
    0.62
     rogue
    0.60
     impactful
    0.60
     synced
    0.59
     intentionally
    0.58
     repurposed
    0.58
     crafting
    0.57
     walkthrough
    0.56
     proactive
    0.55
    POSITIVE LOGITS
    ſ
    0.69
    elerinin
    0.65
     düzey
    0.63
    <0xF4>
    0.62
     variedade
    0.62
    issaient
    0.62
    lerinin
    0.61
     изпол
    0.61
     ſ
    0.61
    asionally
    0.61
    Act Density 0.086%

    No Known Activations