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

    Neuronpedia

    INDEX
    Explanations

    growth and decline

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .inner
    -0.08
    Situation
    -0.08
    XY
    -0.07
    actions
    -0.07
     viande
    -0.07
    פע
    -0.07
    Empire
    -0.07
     situação
    -0.07
     actions
    -0.07
     directives
    -0.07
    POSITIVE LOGITS
     peacefully
    0.09
     kakhulu
    0.09
     kanjani
    0.08
    然
    0.08
     sharply
    0.08
     فيه
    0.08
     lentamente
    0.08
     sõlt
    0.08
     ilalim
    0.07
    Seal
    0.07
    Act Density 0.318%

    No Known Activations