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

    Neuronpedia

    INDEX
    Explanations

    content

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    )↵↵↵
    -0.07
     drawn
    -0.07
    disconnect
    -0.07
     segregated
    -0.06
     hailed
    -0.06
     bunların
    -0.06
    ुलन
    -0.06
    何か
    -0.06
     dime
    -0.06
     Το
    -0.06
    POSITIVE LOGITS
     sanitation
    0.07
     Gir
    0.07
    Tôi
    0.06
    ContentSize
    0.06
     Painter
    0.06
    evenodd
    0.06
    _creator
    0.06
    inement
    0.06
    roma
    0.06
     Launch
    0.06
    Act Density 0.007%

    No Known Activations