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

    Neuronpedia

    INDEX
    Explanations

    сл

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     incest
    -0.06
    िल
    -0.06
    ihn
    -0.06
    Uses
    -0.06
    dropdown
    -0.06
     Rodgers
    -0.06
    >-
    -0.06
     ea
    -0.06
     steady
    -0.06
     væ
    -0.06
    POSITIVE LOGITS
     screenings
    0.07
     ostr
    0.06
    _CON
    0.06
    丹
    0.06
    归
    0.06
    �
    0.06
     Sche
    0.06
     Waiting
    0.06
    	service
    0.06
     конечно
    0.06
    Act Density 0.004%

    No Known Activations