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

    Neuronpedia

    INDEX
    Explanations

    px

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Writer
    -0.07
    fps
    -0.07
    Life
    -0.07
     morb
    -0.07
    (server
    -0.06
    (if
    -0.06
    Seq
    -0.06
    必要
    -0.06
     ');↵↵
    -0.06
    /ml
    -0.06
    POSITIVE LOGITS
     spurred
    0.07
    try
    0.07
     Editorial
    0.06
    صن
    0.06
     osobních
    0.06
     univerz
    0.06
     plav
    0.06
    .psi
    0.06
     дити
    0.06
     gymn
    0.06
    Act Density 0.009%

    No Known Activations