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
    695
    -0.07
     riot
    -0.07
    Feed
    -0.07
     thẳng
    -0.06
    iselect
    -0.06
     yanlış
    -0.06
     घ
    -0.06
    937
    -0.06
     �
    -0.06
    .apple
    -0.06
    POSITIVE LOGITS
     negative
    0.06
     Payments
    0.06
    ingredients
    0.06
    FormControl
    0.06
     Арх
    0.06
    cı
    0.06
    	RTLU
    0.06
    ा।↵↵
    0.06
    InView
    0.06
    Cors
    0.06
    Act Density 0.002%

    No Known Activations