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

    Neuronpedia

    INDEX
    Explanations

    data

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .XPATH
    -0.07
     English
    -0.06
     �
    -0.06
    oredProcedure
    -0.06
     vandal
    -0.06
    きた
    -0.06
    	light
    -0.06
     fractions
    -0.06
     ratios
    -0.06
    Sampling
    -0.06
    POSITIVE LOGITS
     معرف
    0.06
    ούς
    0.06
     sentimental
    0.06
     recipro
    0.06
    餐
    0.06
     자료
    0.06
     CSI
    0.06
     spontaneous
    0.06
     hete
    0.06
    PRESS
    0.06
    Act Density 0.147%

    No Known Activations