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

    Neuronpedia

    INDEX
    Explanations

    1900s years

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Cre
    -0.07
     truth
    -0.06
     Stereo
    -0.06
    -tab
    -0.06
     hated
    -0.06
     QUE
    -0.06
    .topic
    -0.06
     аг
    -0.06
     capsule
    -0.06
     Avoid
    -0.06
    POSITIVE LOGITS
     Croatia
    0.07
    连
    0.07
    ibrary
    0.07
    .springboot
    0.07
    到的
    0.06
     activist
    0.06
     initiatives
    0.06
     вули
    0.06
     Fritz
    0.06
    rupted
    0.06
    Act Density 0.024%

    No Known Activations