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

    Neuronpedia

    INDEX
    Explanations

    analyze

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Baja
    -0.08
     ???
    -0.08
     oto
    -0.07
     Rowling
    -0.07
     Fancy
    -0.07
    )：
    -0.07
    nst
    -0.07
    аются
    -0.07
     主
    -0.07
     biotechnology
    -0.07
    POSITIVE LOGITS
     thoroughly
    0.09
     geometr
    0.09
     mathem
    0.09
     دقیق
    0.08
     Pinn
    0.08
     liquids
    0.08
     мал
    0.07
     לגבי
    0.07
     подробнее
    0.07
    _TEAM
    0.07
    Act Density 0.015%

    No Known Activations