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
    冬
    -0.07
     ratings
    -0.07
     возраста
    -0.07
     Gos
    -0.07
     وك
    -0.07
    кут
    -0.07
    ури
    -0.06
    яется
    -0.06
    	ac
    -0.06
     three
    -0.06
    POSITIVE LOGITS
     patched
    0.07
     condo
    0.07
     Only
    0.06
    裂
    0.06
    aunch
    0.06
     fv
    0.06
    addField
    0.06
    .unsqueeze
    0.06
    arming
    0.06
    (Status
    0.06
    Act Density 0.015%

    No Known Activations