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

    Neuronpedia

    INDEX
    Explanations

    conversational / personal stories

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     وعلى
    -0.07
    כלל
    -0.07
    というのが
    -0.07
    Inverse
    -0.07
    ług
    -0.06
    ｌ
    -0.06
    violent
    -0.06
    มา
    -0.06
    十六条
    -0.06
     unintended
    -0.06
    POSITIVE LOGITS
    关停
    0.07
    romosome
    0.06
    TokenType
    0.06
    ซะ
    0.06
    鼙
    0.06
    emony
    0.06
    	JLabel
    0.06
    翡
    0.06
    �
    0.06
    传染
    0.06
    Act Density 0.076%

    No Known Activations