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

    Neuronpedia

    INDEX
    Explanations

    entry level salaries

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Guard
    0.41
     GUARD
    0.39
     マル
    0.38
     Marcin
    0.37
    ценка
    0.36
     рок
    0.35
    幅度
    0.35
    πό
    0.35
     поступа
    0.35
     коне
    0.35
    POSITIVE LOGITS
     <>
    0.41
     symbolically
    0.41
    ጀ
    0.40
     staring
    0.40
    PACS
    0.39
    entry
    0.39
     stare
    0.39
    osal
    0.38
     gaze
    0.37
     symbolic
    0.37
    Act Density 0.001%

    No Known Activations