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

    Neuronpedia

    INDEX
    Explanations

    ensuite

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     coefficient
    -0.08
    ocurrency
    -0.07
     Diseases
    -0.07
    heets
    -0.07
     anxiety
    -0.07
    现金
    -0.07
    hib
    -0.07
     consent
    -0.07
    Bed
    -0.07
     Excel
    -0.07
    POSITIVE LOGITS
    专心
    0.07
    .uni
    0.07
    private
    0.07
     diff
    0.07
    	aux
    0.06
     inaug
    0.06
    ⌑
    0.06
    FONT
    0.06
     summar
    0.06
    Wrapped
    0.06
    Act Density 0.006%

    No Known Activations