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

    Neuronpedia

    INDEX
    Explanations

    and does

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     şöyle
    0.70
    ManagerProxy
    0.69
    enciar
    0.66
     accomp
    0.66
    𝄞
    0.66
    λλην
    0.65
    ⊷
    0.63
    Michel
    0.62
    ፧
    0.62
    ScreenBinding
    0.62
    POSITIVE LOGITS
     Reader
    0.88
     አለበት
    0.85
     it
    0.83
     It
    0.81
     READER
    0.80
     Understanding
    0.79
    ై
    0.78
     它
    0.78
     nên
    0.77
     нормы
    0.77
    Act Density 0.003%

    No Known Activations