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

    Neuronpedia

    INDEX
    Explanations

    street addresses and zip codes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    LGBT
    0.92
    SAF
    0.89
     বাঙ্গালার
    0.88
    symfony
    0.87
    ㍍
    0.87
    daw
    0.86
    suite
    0.86
    ofthe
    0.86
     generale
    0.85
    dgs
    0.85
    POSITIVE LOGITS
    :
    1.10
    ?
    0.97
     evokes
    0.86
    .
    0.80
     presents
    0.75
     there
    0.73
     is
    0.71
     has
    0.70
     are
    0.68
     unsightly
    0.68
    Act Density 0.003%

    No Known Activations