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

    Neuronpedia

    INDEX
    Explanations

    illustrations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (Output
    -0.07
     고객
    -0.06
     Ninh
    -0.06
    FDA
    -0.06
    	Spring
    -0.06
     Tire
    -0.06
     ประเทศ
    -0.06
     Ί
    -0.06
     repeal
    -0.06
     Switch
    -0.06
    POSITIVE LOGITS
     quam
    0.07
     paar
    0.07
     neighborhoods
    0.06
     cartoon
    0.06
     halves
    0.06
     tranny
    0.06
     daleko
    0.06
     dieses
    0.06
    ENAME
    0.06
    _weak
    0.06
    Act Density 0.007%

    No Known Activations