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

    Neuronpedia

    INDEX
    Explanations

    sympy, python code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ‑
    -0.08
    ையை
    -0.08
    part
    -0.07
    |
    -0.07
    accent
    -0.07
     exhibiting
    -0.07
     perceptions
    -0.07
    -st
    -0.07
     пос
    -0.07
    merged
    -0.07
    POSITIVE LOGITS
     необходимость
    0.08
     cheers
    0.08
     определ
    0.08
     ukuthi
    0.08
    .criteria
    0.08
     zagot
    0.08
    首先
    0.08
     odpr
    0.08
     clás
    0.08
     Frau
    0.08
    Act Density 0.001%

    No Known Activations