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

    Neuronpedia

    INDEX
    Explanations

    IMAGE

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     progn
    -0.06
    .Left
    -0.06
    (locations
    -0.06
     下
    -0.06
     metast
    -0.06
     mw
    -0.06
     registered
    -0.06
    ledik
    -0.06
     amaç
    -0.06
    made
    -0.06
    POSITIVE LOGITS
    =E
    0.07
    ieur
    0.07
    альная
    0.07
    -‐
    0.06
    اسية
    0.06
     прор
    0.06
    ...
↵
    0.06
    UA
    0.06
    ']
    0.06
    inctions
    0.06
    Act Density 0.001%

    No Known Activations