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

    Neuronpedia

    INDEX
    Explanations

    articulate

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     '.$
    -0.07
     ${
    -0.07
    nov
    -0.06
     Vapor
    -0.06
     babies
    -0.06
    '.
    -0.06
     schedules
    -0.06
    xCE
    -0.06
     Sadly
    -0.06
    (cx
    -0.06
    POSITIVE LOGITS
     Merrill
    0.08
    λης
    0.07
     رود
    0.07
     agora
    0.07
     lizard
    0.07
    ΙΚΗ
    0.07
    луги
    0.07
    ูด
    0.07
     قط
    0.07
    čení
    0.06
    Act Density 0.003%

    No Known Activations