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

    Neuronpedia

    INDEX
    Explanations

    forces

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .***.***
    -0.07
     Hague
    -0.07
     gode
    -0.07
    -med
    -0.06
    [ind
    -0.06
     jue
    -0.06
     drastically
    -0.06
     Playground
    -0.06
    Рё
    -0.06
    áč
    -0.06
    POSITIVE LOGITS
     forces
    0.11
    ças
    0.07
    ски
    0.07
     Forces
    0.07
     سكان
    0.06
    netinet
    0.06
    iators
    0.06
    iber
    0.06
    (pdf
    0.06
     {}'.
    0.06
    Act Density 0.011%

    No Known Activations