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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ಛ
    -0.08
    下面
    -0.07
    紅
    -0.07
     degli
    -0.07
    .getClient
    -0.07
     ihrer
    -0.07
     opened
    -0.07
     marc
    -0.07
     �
    -0.07
    Ḩ
    -0.06
    POSITIVE LOGITS
    	usage
    0.07
     informed
    0.07
    😲
    0.07
    .reset
    0.07
     Thinking
    0.07
     saline
    0.07
     jur
    0.07
    坦言
    0.07
    ước
    0.07
    😨
    0.07
    Act Density 0.048%

    No Known Activations