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

    Neuronpedia

    INDEX
    Explanations

    computer code/scripts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Cole
    -0.08
     ż
    -0.07
     submissive
    -0.07
     fkk
    -0.07
    -bed
    -0.07
    agascar
    -0.07
     nghĩ
    -0.07
    944
    -0.07
    671
    -0.07
    676
    -0.06
    POSITIVE LOGITS
    ↵  ↵
    0.08
    )}"↵
    0.06
    	service
    0.06
    _SCHEMA
    0.06
       ↵    ↵
    0.06
    (IService
    0.05
    ↵   ↵
    0.05
    	Command
    0.05
     unnatural
    0.05
     […]↵↵
    0.05
    Act Density 0.000%

    No Known Activations