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

    Neuronpedia

    INDEX
    Explanations

    strategic action and coordination

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     carinatis
    0.41
     Cré
    0.41
     candlest
    0.40
     clickable
    0.40
    ׃
    0.39
     debated
    0.38
     re
    0.38
     Dominique
    0.38
     Nā
    0.38
    相机
    0.38
    POSITIVE LOGITS
    essoa
    0.40
    erase
    0.38
    premium
    0.37
    reproductive
    0.37
    paralle
    0.36
    בים
    0.36
    Strict
    0.36
    pounds
    0.36
    elcome
    0.35
    RegistrationBean
    0.35
    Act Density 0.000%

    No Known Activations