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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Jones
    -0.07
     Pf
    -0.07
     ملف
    -0.07
     agreg
    -0.07
    (USER
    -0.07
     clearance
    -0.06
     spreadsheet
    -0.06
    OWL
    -0.06
    arness
    -0.06
     TREE
    -0.06
    POSITIVE LOGITS
    ♠
    0.07
     ин
    0.06
    。不
    0.06
     gunshot
    0.06
    ]=]
    0.06
     disadv
    0.06
    =sum
    0.06
     barred
    0.06
    꾸
    0.06
     MaterialApp
    0.06
    Act Density 0.004%

    No Known Activations