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

    Neuronpedia

    INDEX
    Explanations

    mathematics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    rophe
    -0.08
     отход
    -0.07
     fica
    -0.07
     Tig
    -0.07
    ेक्ट
    -0.07
    welve
    -0.07
     PAP
    -0.07
     इस्तेमाल
    -0.07
     लागत
    -0.07
     tatt
    -0.07
    POSITIVE LOGITS
     disabilities
    0.08
     qualifies
    0.08
    aine
    0.07
    izam
    0.07
     занят
    0.07
     판단
    0.07
     referencing
    0.07
    ipas
    0.07
    ereg
    0.07
    itala
    0.07
    Act Density 0.026%

    No Known Activations