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

    Neuronpedia

    INDEX
    Explanations

    :

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	FROM
    -0.06
    올
    -0.06
    ミ
    -0.06
    node
    -0.06
    .ro
    -0.06
    ้
    -0.06
     proje
    -0.06
    альных
    -0.06
    dp
    -0.06
     Beitrag
    -0.06
    POSITIVE LOGITS
     stratej
    0.07
     basil
    0.07
     apartment
    0.06
    (resources
    0.06
    	finally
    0.06
    تس
    0.06
    ,body
    0.06
     Sakura
    0.06
    uploader
    0.06
    defaults
    0.06
    Act Density 0.005%

    No Known Activations