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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Ocean
    -0.06
     매우
    -0.06
     armed
    -0.06
    Jan
    -0.06
    745
    -0.06
     thuật
    -0.05
    oct
    -0.05
    екар
    -0.05
    Timer
    -0.05
    Actually
    -0.05
    POSITIVE LOGITS
    	Code
    0.08
     حس
    0.07
     кисл
    0.07
    _Server
    0.07
     گردش
    0.07
    َد
    0.07
     départ
    0.07
     delight
    0.06
    AXB
    0.06
    тон
    0.06
    Act Density 0.000%

    No Known Activations