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

    Neuronpedia

    INDEX
    Explanations

    Likely non-English, political text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -"
    -0.06
    	esc
    -0.06
    Adapter
    -0.06
    =”
    -0.06
    783
    -0.06
     Toni
    -0.06
    -'
    -0.06
    \Dependency
    -0.06
     Debugger
    -0.06
     Yours
    -0.06
    POSITIVE LOGITS
     championships
    0.07
     consumption
    0.07
     assaulted
    0.06
    manufacturer
    0.06
     oppon
    0.06
    .constants
    0.06
     SOLUTION
    0.06
    овер
    0.06
    нул
    0.06
    ansas
    0.06
    Act Density 0.013%

    No Known Activations