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

    Neuronpedia

    INDEX
    Explanations

    save = and scaled Tex

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     কাজকর্ম
    0.43
    Expense
    0.42
     üçüncü
    0.41
    Cooper
    0.39
    メタル
    0.38
    getDefault
    0.38
     আশ্চর্যজনক
    0.38
     Optimum
    0.37
     বিজে
    0.37
     Barrel
    0.37
    POSITIVE LOGITS
     Вин
    0.43
    plante
    0.39
     மண
    0.39
     यंग
    0.38
    有力
    0.38
     Young
    0.38
     simulate
    0.37
    ndown
    0.37
    vr
    0.37
    igraf
    0.36
    Act Density 0.000%

    No Known Activations