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

    Neuronpedia

    INDEX
    Explanations

    surname, names, placeholders

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    。
    0.80
    Ց
    0.71
    Θ
    0.70
    JUST
    0.68
    It
    0.67
    St
    0.65
    צ
    0.65
    ج
    0.64
    Ψ
    0.64
    ف
    0.63
    POSITIVE LOGITS
     surname
    0.70
    ни
    0.66
     Kaduna
    0.64
     их
    0.63
     прожи
    0.63
     remittance
    0.62
     Nevada
    0.61
     their
    0.60
    enderita
    0.60
    o
    0.60
    Act Density 1.128%

    No Known Activations