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

    Neuronpedia

    INDEX
    Explanations

    various contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    тории
    0.42
     endeavor
    0.39
    бов
    0.39
     endeavors
    0.38
    ulse
    0.37
     ×
    0.36
     preservatives
    0.36
    ваться
    0.35
    бере
    0.35
    ленных
    0.35
    POSITIVE LOGITS
     రూ
    0.40
    പ്പെടു
    0.40
    rub
    0.38
    SecurityMarks
    0.37
     kı
    0.37
     ডাউনলোড
    0.37
     RPG
    0.37
     سیا
    0.36
    ania
    0.36
     ಬಹ
    0.35
    Act Density 0.000%

    No Known Activations