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

    Neuronpedia

    INDEX
    Explanations

    ker

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Pacific
    -0.07
    	dialog
    -0.07
     багато
    -0.07
    907
    -0.06
     εκεί
    -0.06
     pokrač
    -0.06
    718
    -0.06
     trench
    -0.06
    entiful
    -0.06
     adventurous
    -0.06
    POSITIVE LOGITS
     airs
    0.07
     ej
    0.07
    emet
    0.06
     HOUSE
    0.06
     House
    0.06
    频
    0.06
    House
    0.06
     Sound
    0.06
    ifference
    0.06
    ế
    0.06
    Act Density 0.007%

    No Known Activations