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

    Neuronpedia

    INDEX
    Explanations

    just saying something

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    честве
    0.39
     ArrayIndex
    0.37
     pivots
    0.37
    ćem
    0.36
     parseFloat
    0.35
    っぱり
    0.35
    шем
    0.35
    োর্ড
    0.34
    ؤلاء
    0.34
     pallets
    0.34
    POSITIVE LOGITS
    <h2>
    0.88
    As
    0.79
    By
    0.73
    <h3>
    0.61
    In
    0.61
    Alright
    0.58
    So
    0.57
    Taking
    0.54
    Having
    0.52
    Alternatively
    0.52
    Act Density 0.000%

    No Known Activations