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

    Neuronpedia

    INDEX
    Explanations

    cabinet and minister

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     كري
    0.44
     নও
    0.42
     مکتی
    0.41
    婭
    0.41
    深圳
    0.40
     verão
    0.40
     среде
    0.40
    একদিন
    0.39
     Mors
    0.39
    शुल्क
    0.39
    POSITIVE LOGITS
     cabinet
    0.58
     cabinets
    0.48
     CABINET
    0.46
     Cabinet
    0.45
    Cabinet
    0.44
    cabinet
    0.44
     regression
    0.41
     extra
    0.41
     revolution
    0.40
     reg
    0.40
    Act Density 0.002%

    No Known Activations