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

    Neuronpedia

    INDEX
    Explanations

    self-improvement

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     především
    -0.07
     DSM
    -0.07
     nghị
    -0.07
     damit
    -0.06
     граф
    -0.06
     Angels
    -0.06
    	img
    -0.06
    alm
    -0.06
    .processor
    -0.06
     ngũ
    -0.06
    POSITIVE LOGITS
    ъек
    0.06
    ฑ
    0.06
    ゴリ
    0.06
     втор
    0.06
    .permission
    0.06
    quires
    0.06
    аров
    0.05
     Details
    0.05
    bron
    0.05
     фран
    0.05
    Act Density 0.572%

    No Known Activations