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

    Neuronpedia

    INDEX
    Explanations

    place names and ethnic groups

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Supp
    0.35
     Concrete
    0.35
     Treated
    0.35
     Venus
    0.35
     Del
    0.34
     Tomato
    0.34
     Ace
    0.34
     Genuine
    0.34
     wy
    0.34
     Pollock
    0.33
    POSITIVE LOGITS
    arg
    0.67
    valment
    0.61
    amer
    0.56
    utas
    0.56
    quir
    0.56
    phthalm
    0.55
    ama
    0.55
    ocaly
    0.54
    amb
    0.54
    ala
    0.54
    Act Density 0.229%

    No Known Activations