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

    Neuronpedia

    INDEX
    Explanations

    money and taxes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     broccoli
    0.41
     bouncy
    0.41
     mites
    0.40
     ساف
    0.40
     incompat
    0.39
     escape
    0.38
     buzzer
    0.38
    acup
    0.38
     unscrupulous
    0.38
    ุ่ม
    0.38
    POSITIVE LOGITS
    astung
    0.54
     Tagen
    0.50
    ாட
    0.49
    Wat
    0.46
    IamPermissions
    0.46
    Zer
    0.46
    meleri
    0.46
    W
    0.46
    kend
    0.46
    mas
    0.45
    Act Density 0.002%

    No Known Activations