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

    Neuronpedia

    INDEX
    Explanations

    anniversaries

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .map
    -0.07
     Watch
    -0.06
    .Ş
    -0.06
    vvm
    -0.06
    rise
    -0.06
    .Ext
    -0.06
     Price
    -0.06
    Coin
    -0.06
     Craft
    -0.06
     Keith
    -0.06
    POSITIVE LOGITS
     тому
    0.07
    �
    0.07
    �
    0.07
    ากล
    0.07
    ‐
    0.07
    ジア
    0.07
    inding
    0.06
    	iVar
    0.06
     controle
    0.06
     заступ
    0.06
    Act Density 0.124%

    No Known Activations