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

    Neuronpedia

    INDEX
    Explanations

    formal writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Bend
    -0.07
    trak
    -0.06
    il
    -0.06
     وات
    -0.06
    lech
    -0.06
    _im
    -0.06
    _courses
    -0.06
    ovit
    -0.06
     Bundy
    -0.06
     fft
    -0.05
    POSITIVE LOGITS
    (tuple
    0.08
     uphol
    0.07
    covers
    0.07
    /type
    0.07
     implication
    0.07
     Sergeant
    0.06
    zhou
    0.06
    utility
    0.06
     stool
    0.06
    繁
    0.06
    Act Density 0.146%

    No Known Activations