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

    Neuronpedia

    INDEX
    Explanations

    "

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Este
    -0.07
    Hey
    -0.06
     condemnation
    -0.06
    시키
    -0.06
    rxjs
    -0.06
     시행
    -0.06
     smoker
    -0.06
     Jahres
    -0.06
    东西
    -0.06
     Honour
    -0.05
    POSITIVE LOGITS
    .parameters
    0.07
    .Buttons
    0.07
     cyclists
    0.06
    `.
    0.06
     vibrations
    0.06
     minors
    0.06
    рет
    0.06
    ********************************************************
    0.06
     pev
    0.06
    	flag
    0.06
    Act Density 0.000%

    No Known Activations