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

    Neuronpedia

    INDEX
    Explanations

    week

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cil
    -0.07
    alus
    -0.06
    ์พ
    -0.06
     stocking
    -0.06
     Prescription
    -0.06
     Ges
    -0.06
    (rate
    -0.06
    งส
    -0.06
    -secret
    -0.06
    ignon
    -0.06
    POSITIVE LOGITS
     мови
    0.06
     곳
    0.06
     주요
    0.06
     week
    0.06
     ticket
    0.06
     c
    0.06
    !↵↵↵↵↵↵
    0.06
    атель
    0.06
     everyone
    0.06
    _ex
    0.06
    Act Density 0.055%

    No Known Activations