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

    Neuronpedia

    INDEX
    Explanations

    powder

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     resultat
    -0.07
    ,),
    -0.07
    מכבי
    -0.06
    བ
    -0.06
    班子成员
    -0.06
    Je
    -0.06
    bindParam
    -0.06
    ᶫ
    -0.06
    深度
    -0.06
    𪟝
    -0.06
    POSITIVE LOGITS
    三星
    0.08
     referencing
    0.08
    ፡
    0.07
     Fargo
    0.07
    	L
    0.07
    /
↵
    0.07
    �
    0.07
     Martin
    0.06
    0.06
    (found
    0.06
    Act Density 0.003%

    No Known Activations