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

    Neuronpedia

    INDEX
    Explanations

    information, updates, account, house

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     netherlands
    0.38
    క్క
    0.38
     findings
    0.37
     helst
    0.37
     লক্ষ্যে
    0.37
    য়ে
    0.37
     permits
    0.36
     refinement
    0.36
    建模
    0.36
    elter
    0.36
    POSITIVE LOGITS
    startGame
    0.43
    gameState
    0.41
    savings
    0.41
     terkenal
    0.39
    Savings
    0.39
    GameState
    0.38
     baptized
    0.38
    memb
    0.38
     এগ
    0.37
    द्रोह
    0.37
    Act Density 0.001%

    No Known Activations