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

    Neuronpedia

    INDEX
    Explanations

    permissions to write

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     iremos
    0.42
     DIY
    0.42
     pyautogui
    0.41
     offering
    0.39
    porto
    0.38
    manual
    0.38
     Decentral
    0.38
     options
    0.37
     Capital
    0.37
     iPhone
    0.37
    POSITIVE LOGITS
    هلاك
    0.45
    搜索
    0.41
    权限
    0.40
    莱
    0.39
     हाइड्र
    0.39
     정확
    0.38
    ดังกล่าว
    0.38
    류
    0.38
    萊
    0.38
    ChatMessage
    0.38
    Act Density 0.032%

    No Known Activations