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

    Neuronpedia

    INDEX
    Explanations

    junction

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     博
    -0.07
    	DB
    -0.07
     CD
    -0.07
    §Ã
    -0.07
     refactor
    -0.07
     PK
    -0.07
    .Ma
    -0.07
     Talks
    -0.06
     }↵↵↵↵↵
    -0.06
     حرکت
    -0.06
    POSITIVE LOGITS
     seiner
    0.06
     harming
    0.06
     lugares
    0.06
     Doors
    0.06
     elev
    0.06
     derechos
    0.06
    ught
    0.06
     sanitary
    0.06
    Edited
    0.05
     Teen
    0.05
    Act Density 0.008%

    No Known Activations