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

    Neuronpedia

    INDEX
    Explanations

    Scientific citations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     giảng
    -0.07
    �
    -0.07
    getKey
    -0.06
     Yet
    -0.06
    .getWidth
    -0.06
     planning
    -0.06
     visa
    -0.06
     intim
    -0.06
     Houses
    -0.06
    	io
    -0.06
    POSITIVE LOGITS
     WANT
    0.06
     Deutsche
    0.06
     apocalypse
    0.06
    worthy
    0.06
    CustomLabel
    0.06
     ống
    0.06
     Symphony
    0.06
     overpower
    0.06
     discarded
    0.06
     neob
    0.06
    Act Density 0.006%

    No Known Activations