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

    Neuronpedia

    INDEX
    Explanations

    emergency helplines or numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Đế
    0.39
     কিছুদিন
    0.37
     rejecting
    0.36
     erred
    0.35
     austen
    0.35
    書類
    0.35
    渣
    0.35
    💎
    0.35
     Minkowski
    0.34
     apiKey
    0.34
    POSITIVE LOGITS
     অথবা
    0.48
     또는
    0.48
    하거나
    0.42
     или
    0.42
     oran
    0.42
    または
    0.41
     alebo
    0.40
    หรือ
    0.39
     または
    0.39
     หรือ
    0.39
    Act Density 0.220%

    No Known Activations