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

    Neuronpedia

    INDEX
    Explanations

    sentencing enhancements

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     amort
    -0.06
    apol
    -0.06
     videa
    -0.06
    權
    -0.06
     Kelvin
    -0.06
    单
    -0.06
    _TOTAL
    -0.06
     وس
    -0.06
     حی
    -0.06
     invest
    -0.06
    POSITIVE LOGITS
     професій
    0.07
     shelters
    0.07
     fringe
    0.07
    ="/">↵
    0.07
     lieu
    0.07
    	register
    0.07
    MainMenu
    0.06
     archivo
    0.06
    trieve
    0.06
    CHKERRQ
    0.06
    Act Density 0.005%

    No Known Activations