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

    Neuronpedia

    INDEX
    Explanations

    code and creative text generation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ity
    0.41
    abs
    0.40
    reports
    0.36
    Alta
    0.36
    ities
    0.33
    ABS
    0.33
    ġ
    0.33
    dauer
    0.33
    لد
    0.33
    ħ
    0.33
    POSITIVE LOGITS
     मैट्रिक
    0.42
    ্যাট
    0.40
     eurozone
    0.39
     rmse
    0.39
     menulis
    0.39
     capitalise
    0.38
     উপনিবেশ
    0.38
    धित
    0.37
     studenti
    0.37
     '='
    0.37
    Act Density 0.000%

    No Known Activations