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

    Neuronpedia

    INDEX
    Explanations

    Code/Serialized data

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ，只
    -0.07
     �
    -0.06
     只
    -0.06
    Liverpool
    -0.06
     새글
    -0.06
    ноп
    -0.06
    _fraction
    -0.06
    	error
    -0.06
     изображ
    -0.06
     ^^
    -0.06
    POSITIVE LOGITS
    ัฐ
    0.07
    च
    0.06
    ламент
    0.06
    imeter
    0.06
    vic
    0.06
     Pres
    0.06
    lanma
    0.06
     Firebase
    0.06
     Muhammad
    0.06
    (Constant
    0.06
    Act Density 0.105%

    No Known Activations