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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    กำล
    -0.07
     ludicrous
    -0.07
    などの
    -0.07
     partnered
    -0.07
    しており
    -0.06
     предпол
    -0.06
    Hopefully
    -0.06
     nose
    -0.06
     Martinez
    -0.06
     креп
    -0.06
    POSITIVE LOGITS
    .loads
    0.06
    Pub
    0.06
    _ads
    0.06
    	content
    0.06
     注
    0.06
     thermometer
    0.06
     แ
    0.06
     might
    0.06
    _sample
    0.06
     may
    0.06
    Act Density 0.010%

    No Known Activations