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

    Neuronpedia

    INDEX
    Explanations

    research

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    auge
    -0.07
    ITTE
    -0.06
    Fit
    -0.06
    263
    -0.06
     support
    -0.06
    	ret
    -0.06
     detect
    -0.06
    ิวเตอร
    -0.06
     Pac
    -0.06
    kar
    -0.06
    POSITIVE LOGITS
     Зем
    0.09
    -,
    0.07
     memiliki
    0.07
    مر
    0.07
     WITHOUT
    0.07
     Playlist
    0.06
     pricing
    0.06
     strokeLine
    0.06
     pubb
    0.06
    Student
    0.06
    Act Density 0.030%

    No Known Activations