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

    Neuronpedia

    INDEX
    Explanations

    code symbols

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -author
    -0.07
     regret
    -0.07
     rat
    -0.07
    Dependencies
    -0.06
    )x
    -0.06
    -limit
    -0.06
    xea
    -0.06
     Medicine
    -0.06
    oidal
    -0.06
     antlr
    -0.06
    POSITIVE LOGITS
     sab
    0.07
     unrest
    0.07
    .getLongitude
    0.06
     doporuč
    0.06
     бес
    0.06
    .experimental
    0.06
    	restore
    0.06
    รอบ
    0.06
    次数
    0.06
     cuối
    0.06
    Act Density 0.056%

    No Known Activations