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

    Neuronpedia

    INDEX
    Explanations

    mid-sentence phrases

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sø
    -0.07
     качестве
    -0.07
    雅
    -0.07
     activism
    -0.06
     greed
    -0.06
    :=
    -0.06
    .__
    -0.06
    ekten
    -0.06
    　　　　　　 　
    -0.06
    _dummy
    -0.06
    POSITIVE LOGITS
     분석
    0.07
     symptoms
    0.07
     pertinent
    0.07
    vetica
    0.07
    	INT
    0.06
    classified
    0.06
     Дон
    0.06
     ادبی
    0.06
     علیه
    0.06
     Materials
    0.06
    Act Density 0.011%

    No Known Activations