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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _ns
    -0.06
     질
    -0.06
    Haz
    -0.06
    liness
    -0.06
     Troy
    -0.06
     exercises
    -0.06
     phosphory
    -0.06
    lings
    -0.06
     index
    -0.06
     rainy
    -0.06
    POSITIVE LOGITS
     unknow
    0.08
     puerto
    0.06
    ]!=
    0.06
    迫
    0.06
    系統
    0.06
    후기
    0.06
    (),'
    0.06
    	M
    0.06
    <![
    0.06
    _claim
    0.06
    Act Density 0.031%

    No Known Activations