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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    носят
    -0.07
    лат
    -0.07
    
    -0.06
    ))*(
    -0.06
     topLeft
    -0.06
    ÜRK
    -0.06
     Anxiety
    -0.06
    محمد
    -0.06
     Neuroscience
    -0.06
     тут
    -0.06
    POSITIVE LOGITS
    (inode
    0.07
    เป
    0.06
    call
    0.06
     dese
    0.06
    (company
    0.06
    ‚
    0.06
     vent
    0.06
     method
    0.06
    ắc
    0.06
    oogle
    0.06
    Act Density 0.001%

    No Known Activations