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

    Neuronpedia

    INDEX
    Explanations

    representation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    GameData
    -0.07
     GUIContent
    -0.06
    	entity
    -0.06
    	Update
    -0.06
    (page
    -0.06
    hos
    -0.06
    formData
    -0.06
    ו�
    -0.06
    우스
    -0.06
     Wang
    -0.06
    POSITIVE LOGITS
     Xm
    0.07
     прив
    0.07
     quil
    0.07
    Error
    0.07
    _EXTENDED
    0.07
    rote
    0.07
     dropped
    0.06
    ­ing
    0.06
     entidad
    0.06
    (Function
    0.06
    Act Density 0.003%

    No Known Activations