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

    Neuronpedia

    INDEX
    Explanations

    data security

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Contest
    -0.07
    ,Integer
    -0.06
    .Vertical
    -0.06
    etAddress
    -0.06
     những
    -0.06
    Checker
    -0.06
    垂
    -0.06
     майже
    -0.06
    卡
    -0.06
     περί
    -0.05
    POSITIVE LOGITS
    _od
    0.07
    asley
    0.07
    /order
    0.07
     genel
    0.06
     flexibility
    0.06
    	model
    0.06
    ر
    0.06
    _w
    0.06
    ,-
    0.06
     bols
    0.06
    Act Density 0.008%

    No Known Activations