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

    Neuronpedia

    INDEX
    Explanations

    code/programming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Islam
    -0.09
     diam
    -0.08
     ик
    -0.08
     ITS
    -0.08
    ขาย
    -0.08
    cket
    -0.07
     diameter
    -0.07
    sy
    -0.07
     puk
    -0.07
    κρα
    -0.07
    POSITIVE LOGITS
     mistakes
    0.09
    Automatically
    0.08
     Fehler
    0.08
    役
    0.08
     automatic
    0.08
     beneath
    0.08
    /errors
    0.08
     Indicates
    0.07
     Ensure
    0.07
     interrupted
    0.07
    Act Density 0.001%

    No Known Activations