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

    Neuronpedia

    INDEX
    Explanations

    simple beauty

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    TOR
    0.82
     intestine
    0.71
     einfach
    0.71
     Filtr
    0.69
    G
    0.69
    ]))
    0.68
    {};
    0.68
     keing
    0.68
    D
    0.68
     Eropa
    0.67
    POSITIVE LOGITS
    ている
    1.04
    ット
    0.98
    ід
    0.95
     possíveis
    0.95
    ส์
    0.93
     janë
    0.93
     resa
    0.88
    ยิน
    0.88
    ABOUT
    0.88
    d
    0.86
    Act Density 0.457%

    No Known Activations